From 6e9f539e4f01153651dd77609b5ccadd44b74df8 Mon Sep 17 00:00:00 2001 From: Ralf Lici Date: Wed, 29 Jul 2026 15:41:30 +0200 Subject: [PATCH 001/116] ovpn: add missing rtnl_link_ops->get_size callback ovpn_fill_info emits IFLA_OVPN_MODE inside IFLA_INFO_DATA, but ovpn_link_ops does not provide a get_size callback. Consequently, rtnetlink's size estimate for ovpn link messages does not include the nested mode attribute. Available skb tailroom may hide this mismatch. When the remaining space is insufficient, however, ovpn_fill_info returns -EMSGSIZE and message construction fails. Add the callback and account for IFLA_OVPN_MODE. Fixes: c2d950c4672a ("ovpn: add basic interface creation/destruction/management routines") Signed-off-by: Ralf Lici Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/main.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 9993c1dfe471..9d9a0ff690d6 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -210,6 +210,12 @@ static int ovpn_newlink(struct net_device *dev, return register_netdevice(dev); } +static size_t ovpn_get_size(const struct net_device *dev) +{ + /* IFLA_OVPN_MODE */ + return nla_total_size(sizeof(u8)); +} + static int ovpn_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ovpn_priv *ovpn = netdev_priv(dev); @@ -228,6 +234,7 @@ static struct rtnl_link_ops ovpn_link_ops = { .policy = ovpn_policy, .maxtype = IFLA_OVPN_MAX, .newlink = ovpn_newlink, + .get_size = ovpn_get_size, .fill_info = ovpn_fill_info, }; From 935dc3bb20e0fee89b598e10d1f5f1f500ddc79a Mon Sep 17 00:00:00 2001 From: Marco Baffo Date: Wed, 22 Jul 2026 06:47:56 +0200 Subject: [PATCH 002/116] ovpn: limit keepalive values to one day Large keepalive values can overflow the delayed-work delay on 32-bit systems, causing the keepalive worker to be repeatedly scheduled. A correct configuration should not require such large keepalive values, and an upper limit of one day is already generous and unnecessary in practice. Limit both the keepalive interval and timeout to 86400 seconds. Signed-off-by: Marco Baffo Signed-off-by: Antonio Quartulli --- Documentation/netlink/specs/ovpn.yaml | 4 ++++ drivers/net/ovpn/netlink-gen.c | 20 ++++++++++++++------ 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/Documentation/netlink/specs/ovpn.yaml b/Documentation/netlink/specs/ovpn.yaml index b0c782e59a32..ac50d1d7c00a 100644 --- a/Documentation/netlink/specs/ovpn.yaml +++ b/Documentation/netlink/specs/ovpn.yaml @@ -118,12 +118,16 @@ attribute-sets: doc: >- The number of seconds after which a keep alive message is sent to the peer + checks: + max: 86400 - name: keepalive-timeout type: u32 doc: >- The number of seconds from the last activity after which the peer is assumed dead + checks: + max: 86400 - name: del-reason type: u32 diff --git a/drivers/net/ovpn/netlink-gen.c b/drivers/net/ovpn/netlink-gen.c index 2147cec7c2c5..92d2fdc17c2e 100644 --- a/drivers/net/ovpn/netlink-gen.c +++ b/drivers/net/ovpn/netlink-gen.c @@ -16,6 +16,14 @@ static const struct netlink_range_validation ovpn_a_peer_id_range = { .max = 16777215ULL, }; +static const struct netlink_range_validation ovpn_a_peer_keepalive_interval_range = { + .max = 86400ULL, +}; + +static const struct netlink_range_validation ovpn_a_peer_keepalive_timeout_range = { + .max = 86400ULL, +}; + static const struct netlink_range_validation ovpn_a_peer_tx_id_range = { .max = 16777215ULL, }; @@ -68,8 +76,8 @@ const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_TX_ID + 1] = { [OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, }, [OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16), [OVPN_A_PEER_LOCAL_PORT] = NLA_POLICY_MIN(NLA_BE16, 1), - [OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, }, - [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, }, + [OVPN_A_PEER_KEEPALIVE_INTERVAL] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_keepalive_interval_range), + [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_keepalive_timeout_range), [OVPN_A_PEER_DEL_REASON] = NLA_POLICY_MAX(NLA_U32, 4), [OVPN_A_PEER_VPN_RX_BYTES] = { .type = NLA_UINT, }, [OVPN_A_PEER_VPN_TX_BYTES] = { .type = NLA_UINT, }, @@ -97,8 +105,8 @@ const struct nla_policy ovpn_peer_new_input_nl_policy[OVPN_A_PEER_TX_ID + 1] = { [OVPN_A_PEER_VPN_IPV6] = NLA_POLICY_EXACT_LEN(16), [OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, }, [OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16), - [OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, }, - [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, }, + [OVPN_A_PEER_KEEPALIVE_INTERVAL] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_keepalive_interval_range), + [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_keepalive_timeout_range), [OVPN_A_PEER_TX_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_tx_id_range), }; @@ -112,8 +120,8 @@ const struct nla_policy ovpn_peer_set_input_nl_policy[OVPN_A_PEER_TX_ID + 1] = { [OVPN_A_PEER_VPN_IPV6] = NLA_POLICY_EXACT_LEN(16), [OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, }, [OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16), - [OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, }, - [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, }, + [OVPN_A_PEER_KEEPALIVE_INTERVAL] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_keepalive_interval_range), + [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_keepalive_timeout_range), [OVPN_A_PEER_TX_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_tx_id_range), }; From 33ec10567fe14456063daf549fdf1a4f53448e4c Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 28 Jul 2026 13:48:47 +0200 Subject: [PATCH 003/116] ovpn: skip rehash for peers already removed from by_id ovpn_nl_peer_set_doit() resolves the target peer via ovpn_peer_get_by_id() before taking ovpn->lock. In the window between the lookup (which only takes a refcount) and the subsequent spin_lock_bh(&ovpn->lock), a concurrent OVPN_CMD_PEER_DEL, keepalive expiry, or socket teardown can take ovpn->lock first, run ovpn_peer_remove() to unhash the peer from all four tables (by_id, by_vpn_addr4/6, by_transp_addr) and release the lock. set_doit then acquires ovpn->lock and calls ovpn_peer_hash_vpn_ip(), which re-inserts the now-removed peer back into the rehashing tables. The same race affects the float path: ovpn_peer_endpoints_update() holds only a refcount and acquires ovpn->lock very late (after async AEAD decrypt and a netlink notification), then rehashes the peer in the by_transp_addr table. The resurrected peer becomes reachable again from the RX lookup (ovpn_peer_get_by_transp_addr) and the TX VPN-IP lookup, even though userspace believes it is gone. Once the data-path refcount drops the peer is freed via call_rcu while the hash entries embedded in it remain linked, opening a UAF window. Bail out of the rehash when hash_entry_id is unhashed, mirroring the sentinel already used by ovpn_peer_remove() to detect the already-removed state. The check is safe under ovpn->lock, which serializes every mutation of hash_entry_id, and is a no-op for the add path because ovpn_peer_add_mp() inserts hash_entry_id before calling ovpn_peer_hash_vpn_ip(). Fixes: 1d36a36f6d53 ("ovpn: implement peer add/get/dump/delete via netlink") Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/peer.c | 73 ++++++++++++++++++++++++----------------- 1 file changed, 43 insertions(+), 30 deletions(-) diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index a21d02ac715e..68021c0c1783 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -297,40 +297,46 @@ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) /* rehashing is required only in MP mode as P2P has one peer * only and thus there is no hashtable */ - if (peer->ovpn->mode == OVPN_MODE_MP) { - spin_lock_bh(&peer->ovpn->lock); - spin_lock_bh(&peer->lock); - bind = rcu_dereference_protected(peer->bind, - lockdep_is_held(&peer->lock)); - if (unlikely(!bind)) { - spin_unlock_bh(&peer->lock); - spin_unlock_bh(&peer->ovpn->lock); - return; - } + if (peer->ovpn->mode != OVPN_MODE_MP) + return; - /* This function may be invoked concurrently, therefore another - * float may have happened in parallel: perform rehashing - * using the peer->bind->remote directly as key - */ + spin_lock_bh(&peer->ovpn->lock); + spin_lock_bh(&peer->lock); + bind = rcu_dereference_protected(peer->bind, + lockdep_is_held(&peer->lock)); + if (unlikely(!bind)) + goto unlock2; - switch (bind->remote.in4.sin_family) { - case AF_INET: - salen = sizeof(*sa); - break; - case AF_INET6: - salen = sizeof(*sa6); - break; - } + /* peer may have been concurrently removed between the caller's + * initial lookup and our acquisition of ovpn->lock; skip the + * rehash so we don't re-insert a removed peer + */ + if (unlikely(hlist_unhashed(&peer->hash_entry_id))) + goto unlock2; - /* remove old hashing */ - hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); - /* re-add with new transport address */ - nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, - &bind->remote, salen); - hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); - spin_unlock_bh(&peer->lock); - spin_unlock_bh(&peer->ovpn->lock); + /* This function may be invoked concurrently, therefore another + * float may have happened in parallel: perform rehashing + * using the peer->bind->remote directly as key + */ + + switch (bind->remote.in4.sin_family) { + case AF_INET: + salen = sizeof(*sa); + break; + case AF_INET6: + salen = sizeof(*sa6); + break; } + + /* remove old hashing */ + hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); + /* re-add with new transport address */ + nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, + &bind->remote, salen); + hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); +unlock2: + spin_unlock_bh(&peer->lock); + spin_unlock_bh(&peer->ovpn->lock); return; unlock: spin_unlock_bh(&peer->lock); @@ -906,6 +912,13 @@ void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer) if (peer->ovpn->mode != OVPN_MODE_MP) return; + /* peer may have been concurrently removed between the caller's + * initial lookup and our acquisition of ovpn->lock; skip the + * rehash so we don't re-insert a removed peer + */ + if (hlist_unhashed(&peer->hash_entry_id)) + return; + if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY)) { /* remove potential old hashing */ hlist_nulls_del_init_rcu(&peer->hash_entry_addr4); From cc12f7240c8c4dee557749d33237542613992f14 Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 28 Jul 2026 13:48:48 +0200 Subject: [PATCH 004/116] ovpn: rehash peer in by_transp_addr table on CMD_PEER_SET When userspace updates a peer's remote endpoint via OVPN_CMD_PEER_SET, ovpn_nl_peer_modify() installs a new ovpn_bind through ovpn_peer_reset_sockaddr(), but ovpn_nl_peer_set_doit() only calls ovpn_peer_hash_vpn_ip() to refresh the VPN-IP hashtables. The peer is left in the bucket of peers->by_transp_addr corresponding to its old remote address. As a consequence, datagrams arriving at the UDP RX path from the newly configured remote hash to a different slot and the lockless lookup in ovpn_peer_get_by_transp_addr() (called from ovpn_udp_encap_recv()) does not find the peer, until either a float event or a peer re-add fixes the bucket. Introduce ovpn_peer_hash_transp_addr() (modeled after ovpn_peer_hash_vpn_ip()) and invoke it from ovpn_nl_peer_set_doit() whenever the request carried a new remote address. The helper bails out in P2P mode and on peers without a bind (TCP), and relies on hlist_nulls_del_init_rcu()'s pprev==NULL short-circuit to handle the case of an entry not currently linked in the table. Fixes: 1d36a36f6d53 ("ovpn: implement peer add/get/dump/delete via netlink") Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/netlink.c | 6 +++ drivers/net/ovpn/peer.c | 105 +++++++++++++++++++++++++------------ drivers/net/ovpn/peer.h | 1 + 3 files changed, 79 insertions(+), 33 deletions(-) diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c index 4c66c1ec497e..4dad85294198 100644 --- a/drivers/net/ovpn/netlink.c +++ b/drivers/net/ovpn/netlink.c @@ -534,6 +534,12 @@ int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info) */ if (ret > 0) ovpn_peer_hash_vpn_ip(peer); + /* if the remote endpoint was updated, the by_transp_addr hash bucket + * also needs to be refreshed, otherwise incoming packets from the new + * remote address would fail the lockless lookup + */ + if (attrs[OVPN_A_PEER_REMOTE_IPV4] || attrs[OVPN_A_PEER_REMOTE_IPV6]) + ovpn_peer_hash_transp_addr(peer); spin_unlock_bh(&ovpn->lock); ovpn_peer_put(peer); diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index 68021c0c1783..a330892e82bf 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -189,6 +189,9 @@ int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer, &(*__tbl1)[ovpn_get_hash_slot(*__tbl1, _key, _key_len)];\ }) +static void __ovpn_peer_hash_transp_addr(struct ovpn_peer *peer, + const struct ovpn_bind *bind); + /** * ovpn_peer_endpoints_update - update remote or local endpoint for peer * @peer: peer to update the remote endpoint for @@ -196,7 +199,6 @@ int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer, */ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) { - struct hlist_nulls_head *nhead; struct sockaddr_storage ss; struct sockaddr_in6 *sa6; bool reset_cache = false; @@ -295,46 +297,23 @@ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) ovpn_nl_peer_float_notify(peer, &ss); /* rehashing is required only in MP mode as P2P has one peer - * only and thus there is no hashtable + * only and thus there is no hashtable. + * + * This function may be invoked concurrently, so re-read peer->bind + * under the proper locks and rehash against its current value. */ if (peer->ovpn->mode != OVPN_MODE_MP) return; + /* This function may be invoked concurrently, therefore another + * float may have happened in parallel: re-acquire the locks and + * rehash using the peer->bind->remote directly as key + */ spin_lock_bh(&peer->ovpn->lock); spin_lock_bh(&peer->lock); bind = rcu_dereference_protected(peer->bind, lockdep_is_held(&peer->lock)); - if (unlikely(!bind)) - goto unlock2; - - /* peer may have been concurrently removed between the caller's - * initial lookup and our acquisition of ovpn->lock; skip the - * rehash so we don't re-insert a removed peer - */ - if (unlikely(hlist_unhashed(&peer->hash_entry_id))) - goto unlock2; - - /* This function may be invoked concurrently, therefore another - * float may have happened in parallel: perform rehashing - * using the peer->bind->remote directly as key - */ - - switch (bind->remote.in4.sin_family) { - case AF_INET: - salen = sizeof(*sa); - break; - case AF_INET6: - salen = sizeof(*sa6); - break; - } - - /* remove old hashing */ - hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); - /* re-add with new transport address */ - nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, - &bind->remote, salen); - hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); -unlock2: + __ovpn_peer_hash_transp_addr(peer, bind); spin_unlock_bh(&peer->lock); spin_unlock_bh(&peer->ovpn->lock); return; @@ -902,6 +881,66 @@ bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb, return match; } +/* Move @peer to the by_transp_addr bucket matching its current bind. + * + * Caller must hold both peer->ovpn->lock and peer->lock, and must have + * already dereferenced a valid (non-NULL) peer->bind, passed in as @bind. + */ +static void __ovpn_peer_hash_transp_addr(struct ovpn_peer *peer, + const struct ovpn_bind *bind) +{ + struct hlist_nulls_head *nhead; + size_t salen; + + lockdep_assert_held(&peer->ovpn->lock); + lockdep_assert_held(&peer->lock); + + if (WARN_ON_ONCE(!bind)) + return; + + /* peer may have been concurrently removed between the caller's + * initial lookup and our acquisition of ovpn->lock; skip the + * rehash so we don't re-insert a removed peer + */ + if (unlikely(hlist_unhashed(&peer->hash_entry_id))) + return; + + switch (bind->remote.in4.sin_family) { + case AF_INET: + salen = sizeof(struct sockaddr_in); + break; + case AF_INET6: + salen = sizeof(struct sockaddr_in6); + break; + default: + return; + } + + /* remove old hashing (no-op if entry is not currently linked) */ + hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); + /* re-add with current transport address */ + nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, + &bind->remote, salen); + hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); +} + +void ovpn_peer_hash_transp_addr(struct ovpn_peer *peer) +{ + struct ovpn_bind *bind; + + lockdep_assert_held(&peer->ovpn->lock); + + /* rehashing makes sense only in multipeer mode */ + if (peer->ovpn->mode != OVPN_MODE_MP) + return; + + spin_lock_bh(&peer->lock); + bind = rcu_dereference_protected(peer->bind, + lockdep_is_held(&peer->lock)); + __ovpn_peer_hash_transp_addr(peer, bind); + spin_unlock_bh(&peer->lock); +} + void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer) { struct hlist_nulls_head *nhead; diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h index 86c8cffada6d..dfa5c0037e02 100644 --- a/drivers/net/ovpn/peer.h +++ b/drivers/net/ovpn/peer.h @@ -150,6 +150,7 @@ struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id); struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn, struct sk_buff *skb); void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer); +void ovpn_peer_hash_transp_addr(struct ovpn_peer *peer); bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb, struct ovpn_peer *peer); From 59aed1eb60d70678a53acccb0cb337a26ce6680e Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 28 Jul 2026 13:48:50 +0200 Subject: [PATCH 005/116] ovpn: ensure socket is owned by ovpn before deref sk_user_data Some subsystems, like BPF SOCKMAP, set sk_user_data without actually setting the encap_type. For this reason, we must make sure that the type is the one ovpn expects before dereferencing sk_user_data. Failing to do so may lead to out-of-bounds reads. Fixes: f6226ae7a0cd ("ovpn: introduce the ovpn_socket object") Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/socket.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c index 517caa64a4fe..6cbeb2caaeec 100644 --- a/drivers/net/ovpn/socket.c +++ b/drivers/net/ovpn/socket.c @@ -162,6 +162,15 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer) rcu_read_lock(); ovpn_sock = rcu_dereference_sk_user_data(sk); if (ovpn_sock) { + /* something else filled the sk_user_data without + * setting the encap_type. Reject the socket. + */ + if (!type) { + ovpn_sock = ERR_PTR(-EBUSY); + rcu_read_unlock(); + goto sock_release; + } + /* socket owned by another ovpn instance, we can't use it */ if (ovpn_sock->ovpn != peer->ovpn) { ovpn_sock = ERR_PTR(-EBUSY); From 3f012bdbabe211ccbc0c50ea5a1dbc60f8af1532 Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 28 Jul 2026 13:48:51 +0200 Subject: [PATCH 006/116] ovpn: zero-initialize sockaddr before learning a floated endpoint ovpn_peer_endpoints_update() builds the new remote endpoint in an on-stack struct sockaddr_storage that is left uninitialized. For IPv4 only sin_family/sin_addr/sin_port are written, leaving the 8-byte sin_zero padding as stack garbage (for IPv6, sin6_flowinfo is left uninitialized likewise). ovpn_peer_reset_sockaddr() -> ovpn_bind_from_sockaddr() then memcpy()s sizeof(struct sockaddr_in)/sizeof(struct sockaddr_in6) bytes - padding included - into bind->remote. That buffer is later hashed with jhash() over the same length to place the peer in the by_transp_addr table, so the garbage padding lands the floated peer in an essentially random bucket. Lockless lookups in ovpn_peer_get_by_transp_addr() build their key from a zero-initialized sockaddr_storage, compute a different bucket and fail to find the peer. This is also a plain use of uninitialized stack memory in jhash(). Build the floated endpoint with a designated initializer so the padding (sin_zero for IPv4, sin6_flowinfo for IPv6) is zeroed as part of the assignment. This keeps the padding out of the by_transp_addr hash key without memset-ing the whole sockaddr_storage on every received packet. Fixes: f0281c1d3732 ("ovpn: add support for updating local or remote UDP endpoint") Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/peer.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index a330892e82bf..33fb0a75e600 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -222,9 +222,16 @@ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) */ local_ip = &ip_hdr(skb)->daddr; sa = (struct sockaddr_in *)&ss; - sa->sin_family = AF_INET; - sa->sin_addr.s_addr = ip_hdr(skb)->saddr; - sa->sin_port = udp_hdr(skb)->source; + /* use a designated initializer so the sin_zero padding + * is zeroed (it ends up in the by_transp_addr hash key) + * without memset-ing the whole sockaddr_storage on the + * RX fast path + */ + *sa = (struct sockaddr_in) { + .sin_family = AF_INET, + .sin_addr.s_addr = ip_hdr(skb)->saddr, + .sin_port = udp_hdr(skb)->source, + }; salen = sizeof(*sa); reset_cache = true; break; @@ -250,11 +257,19 @@ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) */ local_ip = &ipv6_hdr(skb)->daddr; sa6 = (struct sockaddr_in6 *)&ss; - sa6->sin6_family = AF_INET6; - sa6->sin6_addr = ipv6_hdr(skb)->saddr; - sa6->sin6_port = udp_hdr(skb)->source; - sa6->sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->saddr, - skb->skb_iif); + /* use a designated initializer so the sin6_flowinfo + * padding is zeroed (it ends up in the by_transp_addr + * hash key) without memset-ing the whole + * sockaddr_storage on the RX fast path + */ + *sa6 = (struct sockaddr_in6) { + .sin6_family = AF_INET6, + .sin6_addr = ipv6_hdr(skb)->saddr, + .sin6_port = udp_hdr(skb)->source, + .sin6_scope_id = + ipv6_iface_scope_id(&ipv6_hdr(skb)->saddr, + skb->skb_iif), + }; salen = sizeof(*sa6); reset_cache = true; break; From b47a52dcd598a50207a33df304acdf45348a690f Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 28 Jul 2026 13:48:52 +0200 Subject: [PATCH 007/116] ovpn: hash floated peer by transport identity only The by_transp_addr table is keyed on the peer's remote transport address, but the float rehash hashed bind->remote directly, while the two other sites that touch the table build a clean key first: ovpn_peer_add_mp() and the lookup in ovpn_peer_get_by_transp_addr() both hash a sockaddr holding only family/address/port. For a link-local IPv6 peer, bind->remote carries sin6_scope_id (set from ipv6_iface_scope_id() when the endpoint is learned), and that field is folded into the jhash() over sizeof(struct sockaddr_in6). The lookup never sets sin6_scope_id, so after such a peer floats it is rehashed into a scope_id-dependent bucket that lookups (scope_id 0) never visit, making the peer unreachable through the by_transp_addr fallback. ovpn_peer_transp_match() only compares address and port, so the hash was keying on a field the match ignores. sin6_scope_id must stay in bind->remote because the TX path uses it as flowi6_oif, so it cannot just be cleared there. Instead build the hash key from family/address/port only, exactly like ovpn_peer_add_mp() and the lookup, so all three sites agree on the bucket. Fixes: f0281c1d3732 ("ovpn: add support for updating local or remote UDP endpoint") Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/peer.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index 33fb0a75e600..eada414a9d92 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -904,7 +904,10 @@ bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb, static void __ovpn_peer_hash_transp_addr(struct ovpn_peer *peer, const struct ovpn_bind *bind) { + struct sockaddr_storage sa = {}; struct hlist_nulls_head *nhead; + struct sockaddr_in6 *sa6; + struct sockaddr_in *sa4; size_t salen; lockdep_assert_held(&peer->ovpn->lock); @@ -920,12 +923,26 @@ static void __ovpn_peer_hash_transp_addr(struct ovpn_peer *peer, if (unlikely(hlist_unhashed(&peer->hash_entry_id))) return; + /* Build the hash key from the transport identity only + * (family/address/port), matching ovpn_peer_add_mp() and the lookup + * in ovpn_peer_get_by_transp_addr(). Hashing bind->remote directly + * would fold in sin6_scope_id (set on the float path but never by the + * lookup), scattering the peer into a bucket lookups cannot reach. + */ switch (bind->remote.in4.sin_family) { case AF_INET: - salen = sizeof(struct sockaddr_in); + sa4 = (struct sockaddr_in *)&sa; + sa4->sin_family = AF_INET; + sa4->sin_addr.s_addr = bind->remote.in4.sin_addr.s_addr; + sa4->sin_port = bind->remote.in4.sin_port; + salen = sizeof(*sa4); break; case AF_INET6: - salen = sizeof(struct sockaddr_in6); + sa6 = (struct sockaddr_in6 *)&sa; + sa6->sin6_family = AF_INET6; + sa6->sin6_addr = bind->remote.in6.sin6_addr; + sa6->sin6_port = bind->remote.in6.sin6_port; + salen = sizeof(*sa6); break; default: return; @@ -934,8 +951,8 @@ static void __ovpn_peer_hash_transp_addr(struct ovpn_peer *peer, /* remove old hashing (no-op if entry is not currently linked) */ hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); /* re-add with current transport address */ - nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, - &bind->remote, salen); + nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, &sa, + salen); hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); } From 0301aa324941698bec3dd455df1c5abc7afb10db Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 28 Jul 2026 13:48:53 +0200 Subject: [PATCH 008/116] ovpn: disable IPv4 redirects on MP interfaces ovpn_mp_alloc() tried to disable SEND_REDIRECTS on a multipeer interface, but it runs from ovpn_net_init() (->ndo_init), which register_netdevice() invokes before the NETDEV_REGISTER notifier chain. The IPv4 in_device is only created when that notifier reaches inetdev_event() -> inetdev_init(), so __in_dev_get_rtnl() always returned NULL at ndo_init time and the whole redirect-disabling block (both the per-device and the per-netns IPV4_DEVCONF_ALL write) was dead. MP interfaces therefore kept emitting ICMP redirects. Disabling redirects only once is not enough either: the IPv4 in_device is destroyed and recreated when the interface is moved to a different network namespace (NETDEV_UNREGISTER/NETDEV_REGISTER), and the newly created in_device inherits the destination namespace defaults, silently re-enabling SEND_REDIRECTS. Disable redirects from ovpn_net_open() (->ndo_open) instead: it runs every time the interface is brought up, including after the in_device has been recreated, so the setting is always re-applied. This mirrors what wireguard does in wg_open(). RTNL is held on the ndo_open() path, so __in_dev_get_rtnl() is safe. Fixes: 05003b408c20 ("ovpn: implement multi-peer support") Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/main.c | 50 ++++++++++++++++++++++++++++------------- 1 file changed, 35 insertions(+), 15 deletions(-) diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 9d9a0ff690d6..3a04757d5c31 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -35,25 +35,11 @@ static void ovpn_priv_free(struct net_device *net) static int ovpn_mp_alloc(struct ovpn_priv *ovpn) { - struct in_device *dev_v4; int i; if (ovpn->mode != OVPN_MODE_MP) return 0; - dev_v4 = __in_dev_get_rtnl(ovpn->dev); - if (dev_v4) { - /* disable redirects as Linux gets confused by ovpn - * handling same-LAN routing. - * This happens because a multipeer interface is used as - * relay point between hosts in the same subnet, while - * in a classic LAN this would not be needed because the - * two hosts would be able to talk directly. - */ - IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); - IPV4_DEVCONF_ALL(dev_net(ovpn->dev), SEND_REDIRECTS) = false; - } - /* the peer container is fairly large, therefore we allocate it only in * MP mode */ @@ -97,9 +83,38 @@ static void ovpn_net_uninit(struct net_device *dev) gro_cells_destroy(&ovpn->gro_cells); } +static int ovpn_net_open(struct net_device *dev) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + struct in_device *dev_v4; + + /* the IPv4 in_device (and thus its config) is recreated whenever the + * interface is moved to a new netns, so redirects must be disabled on + * every bring-up rather than once at creation time, otherwise the + * setting is silently lost after such a move + */ + if (ovpn->mode == OVPN_MODE_MP) { + dev_v4 = __in_dev_get_rtnl(dev); + if (dev_v4) { + /* disable redirects as Linux gets confused by ovpn + * handling same-LAN routing. + * This happens because a multipeer interface is used as + * relay point between hosts in the same subnet, while + * in a classic LAN this would not be needed because the + * two hosts would be able to talk directly. + */ + IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); + IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false; + } + } + + return 0; +} + static const struct net_device_ops ovpn_netdev_ops = { .ndo_init = ovpn_net_init, .ndo_uninit = ovpn_net_uninit, + .ndo_open = ovpn_net_open, .ndo_start_xmit = ovpn_net_xmit, }; @@ -183,6 +198,7 @@ static int ovpn_newlink(struct net_device *dev, struct ovpn_priv *ovpn = netdev_priv(dev); struct nlattr **data = params->data; enum ovpn_mode mode = OVPN_MODE_P2P; + int ret; if (data && data[IFLA_OVPN_MODE]) { mode = nla_get_u8(data[IFLA_OVPN_MODE]); @@ -207,7 +223,11 @@ static int ovpn_newlink(struct net_device *dev, else netif_carrier_off(dev); - return register_netdevice(dev); + ret = register_netdevice(dev); + if (ret < 0) + return ret; + + return 0; } static size_t ovpn_get_size(const struct net_device *dev) From 4680c0ebd958fc18e53c8b91d80436b236a8fc09 Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 28 Jul 2026 13:48:54 +0200 Subject: [PATCH 009/116] ovpn: ensure TCP vars are initialized first Netlink calls may access TCP global vars (i.e. when attaching a TCP socket), therefore we need to make sure the latters are initialized beforehand. For this reason move the global TCP initialization at the top of the module init function. Fixes: 11851cbd60ea ("ovpn: implement TCP transport") Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 3a04757d5c31..168cfe9b59a9 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -260,8 +260,11 @@ static struct rtnl_link_ops ovpn_link_ops = { static int __init ovpn_init(void) { - int err = rtnl_link_register(&ovpn_link_ops); + int err; + ovpn_tcp_init(); + + err = rtnl_link_register(&ovpn_link_ops); if (err) { pr_err("ovpn: can't register rtnl link ops: %d\n", err); return err; @@ -273,8 +276,6 @@ static int __init ovpn_init(void) goto unreg_rtnl; } - ovpn_tcp_init(); - return 0; unreg_rtnl: From 26ba17d845193dac4921ae1ab280d28d1938052e Mon Sep 17 00:00:00 2001 From: Qingfang Deng Date: Fri, 24 Jul 2026 09:49:26 +0800 Subject: [PATCH 010/116] ovpn: fix incorrect use of rcu_access_pointer() rcu_access_pointer() should only be used to test the value of a pointer, not to dereference it. As it's in a spin_lock_bh() critical section, use rcu_dereference_bh() instead, avoiding an extra rcu_read_lock(). Fixes: f6226ae7a0cd ("ovpn: introduce the ovpn_socket object") Signed-off-by: Qingfang Deng Signed-off-by: Antonio Quartulli --- drivers/net/ovpn/peer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index eada414a9d92..b0519f9840d8 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -1249,7 +1249,7 @@ static void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk, } if (sk) { - ovpn_sock = rcu_access_pointer(peer->sock); + ovpn_sock = rcu_dereference_bh(peer->sock); if (!ovpn_sock || ovpn_sock->sk != sk) { spin_unlock_bh(&ovpn->lock); return; From 3860d8748af315bfee6fe669fddc1fc17d3214db Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Fri, 24 Jul 2026 17:30:36 +0800 Subject: [PATCH 011/116] net: hns3: fix speed configuration residue after driver reload After setting a 100G optical port to 40G via ethtool and reloading the driver, the port remains at 40G instead of reverting to the firmware default speed of 100G. The commit referenced in Fixes: added two overwrites in hclge_init_ae_dev() for non-copper media, so that optical ports connected to forced-mode remotes inherit the firmware-preset autoneg and speed instead of the hardcoded defaults: req_autoneg = mac.autoneg req_speed = mac.speed (when autoneg disabled) The autoneg overwrite keeps existing behavior: hclge_set_autoneg_speed_dup() already uses mac.autoneg (not req_autoneg) since it was introduced, so autoneg inheritance from firmware was already in place. This part is kept. The speed overwrite, however, introduces the residue: mac.speed reflects whatever was last programmed into the MAC, and after unload firmware does not restore the MAC speed to the flash default. So if the user changed speed via ethtool in a prior load, mac.speed still carries that value on reload and req_speed inherits it. Fix by dropping the req_speed overwrite only. req_speed keeps the firmware default value set in hclge_configure() (cfg.default_speed), so a reload reverts the speed to default, matching the expectation that a driver reload resets link configuration. Trade-off: on optical ports whose firmware default speed does not match a forced-mode remote, reload now drops the link and the user must re-apply ethtool configuration. This is acceptable: a driver reload is expected to reset link configuration, not to inherit runtime state from before unload. The autoneg inheritance is left in place as established behavior; changing it is out of scope for this patch and would itself be a user-perceivable behavior change. Fixes: d9d349c4e8a0 ("net: hns3: differentiate autoneg default values between copper and fiber") Signed-off-by: Jijie Shao Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260724093036.426631-1-shaojijie@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index fc8587c80813..164c3ecf195c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9498,12 +9498,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) if (ret) goto err_ptp_uninit; - if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_COPPER) { + if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_COPPER) hdev->hw.mac.req_autoneg = hdev->hw.mac.autoneg; - if (hdev->hw.mac.autoneg == AUTONEG_DISABLE && - hdev->hw.mac.speed != SPEED_UNKNOWN) - hdev->hw.mac.req_speed = hdev->hw.mac.speed; - } ret = hclge_set_autoneg_speed_dup(hdev); if (ret) { From 1881f2efbf7f78dc0a79a387b29fde6ff56d3731 Mon Sep 17 00:00:00 2001 From: Fan Ye Date: Mon, 27 Jul 2026 12:29:48 +0000 Subject: [PATCH 012/116] Revert "net: thunderbolt: Enable end-to-end flow control also in transmit" This reverts commit a8065af3346ebd7c76ebc113451fb3ba94cf7769. Per the USB4 spec, a Transmit Descriptor Ring with E2E flow control disabled does not require any credits to be available before the Host Interface Adapter Layer transmits a tunneled packet from it. Once E2E is enabled on that ring the controller must first obtain end-to-end credits. The ASMedia ASM4242 USB4 host router (PCI 1b21:2425) never delivers those credits. The controller does accept the configuration: reading the ring OPTIONS register back right after tb_ring_start() returns exactly what was written, including RING_FLAG_E2E_FLOW_CONTROL (bit 28) and the E2E HopID field. No credit ever arrives though, so the Tx ring's hardware consumer index never advances and the link carries no traffic at all. Measured on two hosts connected point to point, onboard ASM4242 on MSI X870E and X870, v6.17, stock drivers/net/thunderbolt/main.c with only this revert applied on top: before: 100% packet loss to the peer; thunderbolt0 is up and the XDomain handshake completes ("new host found"), but iperf3 fails with "No route to host" once the neighbour entry expires after: 0% packet loss, 0.28 ms RTT; iperf3 4.21 Gb/s one way and 5.17 Gb/s the other (5 runs each, stddev <= 0.02), 1 retransmit in 10 s An instrumented build additionally showed a frozen-Tx-consumer watchdog firing ~30k times in a 10 s window before this change. Rx-side E2E is not touched by this revert, so peers that do return credits keep receive-side flow control. ASMedia does not look like an isolated case. The out-of-tree thunderbolt-ibverbs project disables native E2E on AMD NHI by default, noting that "Strix Halo has reproduced TX completion wedges with multiple native E2E rings active" -- the same failure mode, on a different vendor. Since the driver has no way to tell in advance which host router returns the credits, going back to the previous behaviour looks safer than adding a quirk per affected part; Tx-side E2E can be reintroduced as an opt-in for controllers that are known to implement the credit return. Note that the reverted commit was not fixing a reported problem, it was derived from the spec wording alone, so this revert is not expected to regress a known workload. Cc'ing the original author in case there was one. Fixes: a8065af3346e ("net: thunderbolt: Enable end-to-end flow control also in transmit") Cc: zhangjianrong Signed-off-by: Fan Ye Acked-by: Mika Westerberg Link: https://patch.msgid.link/20260727123002.25225-1-fy15309206903@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/thunderbolt/main.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/thunderbolt/main.c b/drivers/net/thunderbolt/main.c index 02a91650561a..c5670d61820c 100644 --- a/drivers/net/thunderbolt/main.c +++ b/drivers/net/thunderbolt/main.c @@ -925,12 +925,8 @@ static int tbnet_open(struct net_device *dev) netif_carrier_off(dev); - flags = RING_FLAG_FRAME; - /* Only enable full E2E if the other end supports it too */ - if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E) - flags |= RING_FLAG_E2E; - - ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags); + ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, + RING_FLAG_FRAME); if (!ring) { netdev_err(dev, "failed to allocate Tx ring\n"); return -ENOMEM; @@ -949,6 +945,11 @@ static int tbnet_open(struct net_device *dev) sof_mask = BIT(TBIP_PDF_FRAME_START); eof_mask = BIT(TBIP_PDF_FRAME_END); + flags = RING_FLAG_FRAME; + /* Only enable full E2E if the other end supports it too */ + if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E) + flags |= RING_FLAG_E2E; + ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags, net->tx_ring.ring->hop, sof_mask, eof_mask, tbnet_start_poll, net); From 683c6ba6e58e6ed1037831ea97dd58d9c0e76b8d Mon Sep 17 00:00:00 2001 From: "Xiang Mei (Microsoft)" Date: Sat, 25 Jul 2026 23:39:30 +0000 Subject: [PATCH 013/116] bonding: alb: re-check primary_is_promisc under RTNL in bond_alb_monitor bond_alb_monitor() reads primary_is_promisc under RCU, then drops RCU and takes RTNL via rtnl_trylock() before undoing the promiscuity it set on the active slave. In that window the active slave can change under RTNL (RTM_DELLINK -> __bond_release_one() -> bond_alb_handle_active_change()), which already drops the promiscuity and clears primary_is_promisc. The monitor still acts on the stale decision: if the slave was removed with no failover, curr_active_slave is now NULL and the deref faults; if it failed over, the stale dev_set_promiscuity(-1) underflows the new slave's promiscuity counter and pins it in IFF_PROMISC. Oops: general protection fault, probably for non-canonical address ... KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] Workqueue: b42 bond_alb_monitor RIP: 0010:bond_alb_monitor (drivers/net/bonding/bond_alb.c:1600) process_one_work (kernel/workqueue.c:3322) worker_thread (kernel/workqueue.c:3486) kthread (kernel/kthread.c:436) ret_from_fork (arch/x86/kernel/process.c:158) Kernel panic - not syncing: Fatal exception Re-check primary_is_promisc (and curr_active_slave) after taking RTNL so the monitor only undoes an increment it still owns. The other bonding monitors already re-read state under RTNL in their commit phase (bond_miimon_commit/bond_ab_arp_commit); bond_alb_monitor() was the only one acting on the pre-trylock decision. Fixes: d0e81b7e2246 ("bonding: Acquire correct locks in alb for promisc change") Reported-by: AutonomousCodeSecurity@microsoft.com Signed-off-by: Xiang Mei (Microsoft) Reviewed-by: Nikolay Aleksandrov Acked-by: Jay Vosburgh Link: https://patch.msgid.link/20260725233930.2957317-1-xmei5@asu.edu Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_alb.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 2d37b07c8215..839f7482dc18 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1534,8 +1534,8 @@ void bond_alb_monitor(struct work_struct *work) struct bonding *bond = container_of(work, struct bonding, alb_work.work); struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct slave *slave, *curr; struct list_head *iter; - struct slave *slave; if (!bond_has_slaves(bond)) { atomic_set(&bond_info->tx_rebalance_counter, 0); @@ -1597,9 +1597,11 @@ void bond_alb_monitor(struct work_struct *work) * because a slave was disabled then * it can now leave promiscuous mode. */ - dev_set_promiscuity(rtnl_dereference(bond->curr_active_slave)->dev, - -1); - bond_info->primary_is_promisc = 0; + curr = rtnl_dereference(bond->curr_active_slave); + if (bond_info->primary_is_promisc && curr) { + dev_set_promiscuity(curr->dev, -1); + bond_info->primary_is_promisc = 0; + } rtnl_unlock(); rcu_read_lock(); From 53a43508ee332d8bffe40590c3d189c92a551f9f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 27 Jul 2026 12:19:37 +0100 Subject: [PATCH 014/116] net: devmem: prevent net-iov / page mixing We should either have net_iov or page backed frags in a single skb, otherwise it blows up down the stack. Don't allow mixing in zerocopy_fill_skb_from_devmem(). Fixes: bd61848900bff ("net: devmem: Implement TX path") Cc: stable@vger.kernel.org Signed-off-by: Pavel Begunkov Acked-by: Stanislav Fomichev Reviewed-by: Mina Almasry Reviewed-by: Bobby Eshleman Link: https://patch.msgid.link/e3199788c4732545627a4721097ebb71ad737bab.1785150502.git.asml.silence@gmail.com Signed-off-by: Jakub Kicinski --- net/core/datagram.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/datagram.c b/net/core/datagram.c index c285c6465923..173b5d97bd40 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -712,6 +712,9 @@ zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from, size_t virt_addr, size, off; struct net_iov *niov; + if (i && skb_frags_readable(skb)) + return -EFAULT; + /* Devmem filling works by taking an IOVEC from the user where the * iov_addrs are interpreted as an offset in bytes into the dma-buf to * send from. We do not support other iter types. From c2707480cfbf19c7619acc9c089d17f20869821f Mon Sep 17 00:00:00 2001 From: Doruk Tan Ozturk Date: Fri, 24 Jul 2026 16:40:15 +0200 Subject: [PATCH 015/116] net/packet: reset the MAC header on the packet-socket transmit path packet_parse_headers() resets the MAC header only for a SOCK_RAW frame whose socket did not bind a protocol. A protocol-bound SOCK_RAW socket, any SOCK_DGRAM frame, and the legacy SOCK_PACKET path therefore leave skb->mac_header unset here. For frames sent via __dev_queue_xmit() this is harmless: it resets the MAC header unconditionally. But the packet-socket PACKET_QDISC_BYPASS path uses dev_direct_xmit(), which does not, so the frame reaches ndo_start_xmit() with the MAC header unset. A driver that reads eth_hdr(skb) on transmit then dereferences skb->head + (u16)~0, an out-of-bounds access ~64 KiB past the head -- the same class fixed for one consumer in commit f5089008f90c ("macsec: do not read an unset MAC header in macsec_encrypt()"). packet_parse_headers() runs only on the transmit path, where skb->data points at the start of the L2 header for every packet-socket type regardless of its length: SOCK_RAW and SOCK_PACKET carry a user-supplied header and SOCK_DGRAM has one built by dev_hard_header(). Reset the MAC header unconditionally, mirroring __dev_queue_xmit(), so the frame is anchored on the bypass path too. Found by 0sec (https://0sec.ai) using automated source analysis; verified against source and matched to the macsec KASAN report in f5089008f90c. Compile-tested. Fixes: 75c65772c3d1 ("net/packet: Ask driver for protocol if not provided by user") Cc: stable@vger.kernel.org Signed-off-by: Doruk Tan Ozturk Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260724144015.63219-1-doruk@0sec.ai Signed-off-by: Jakub Kicinski --- net/packet/af_packet.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e75d2932475a..5ae0511e89e3 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1924,11 +1924,12 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; + /* On TX skb->data is the L2 header; anchor it for all socket types. */ + skb_reset_mac_header(skb); + if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && - sock->type == SOCK_RAW) { - skb_reset_mac_header(skb); + sock->type == SOCK_RAW) skb->protocol = dev_parse_header_protocol(skb); - } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && From ec680ea4ba1bca92a767fb7e7869758bfdd886e3 Mon Sep 17 00:00:00 2001 From: Satish Kharat Date: Mon, 27 Jul 2026 23:26:30 -0700 Subject: [PATCH 016/116] enic: fix tx_hang_reset use-after-free on device removal enic_remove() cancels the reset and change_mtu_work items but does not cancel tx_hang_reset. A TX timeout that fires while the device is being removed can schedule enic_tx_hang_reset() so that it runs after free_netdev(), resulting in a use-after-free. cancel_work_sync() alone is not sufficient here: the still-live watchdog and notify paths can re-schedule these work items in the window between the cancel and unregister_netdev(). Use disable_work_sync(), which cancels the work and blocks any subsequent schedule_work() from requeuing it, and apply it to the reset and change_mtu_work items as well so the same requeue race is closed for all teardown work. Fixes: 937317c7c109 ("enic: do hang reset only in case of tx timeout") Signed-off-by: Satish Kharat Link: https://patch.msgid.link/20260728062730.2394873-1-satishkh@cisco.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cisco/enic/enic_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index e7125b818087..d98f7e7ccab9 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -3011,8 +3011,9 @@ static void enic_remove(struct pci_dev *pdev) if (netdev) { struct enic *enic = netdev_priv(netdev); - cancel_work_sync(&enic->reset); - cancel_work_sync(&enic->change_mtu_work); + disable_work_sync(&enic->reset); + disable_work_sync(&enic->tx_hang_reset); + disable_work_sync(&enic->change_mtu_work); unregister_netdev(netdev); enic_dev_deinit(enic); vnic_dev_close(enic->vdev); From 6ddfba2ea98db21b001e0e5c472499156224650c Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 28 Jul 2026 07:43:38 +0300 Subject: [PATCH 017/116] net/mlx5e: TC, Check if flow is PEER before acquiring devcom lock In case __mlx5e_add_fdb_flow() fails in lower levels, the flow is deleted via mlx5e_tc_del_flow(), and mlx5e_tc_del_flow() is acquiring ESW devcom lock without condition. In addition, in case of peer_flow, __mlx5e_add_fdb_flow() is called while holding ESW devcom comp lock. This results in an AA deadlock. To fix this, introduce a new PEER flag that is set on flows created as peer flows (the duplicate flows on peer devices), and check it in mlx5e_tc_del_flow() before acquiring ESW devcom lock. Lockdep splat: ============================================ WARNING: possible recursive locking detected ============================================ Possible unsafe locking scenario: CPU0 ---- lock(&comp->lock_key#2); lock(&comp->lock_key#2); *** DEADLOCK *** Call Trace: dump_stack_lvl+0x69/0xa0 print_deadlock_bug.cold+0xbd/0xca __lock_acquire+0x1671/0x2ec0 lock_acquire+0x10e/0x2e0 down_read+0x95/0x430 mlx5_devcom_for_each_peer_begin+0x4e/0xe0 [mlx5_core] mlx5e_tc_del_flow+0x11d/0xa70 [mlx5_core] mlx5e_flow_put+0x99/0x100 [mlx5_core] __mlx5e_add_fdb_flow+0x409/0xf00 [mlx5_core] mlx5e_configure_flower+0x2a86/0x4100 [mlx5_core] mlx5e_rep_setup_tc_cls_flower+0x12f/0x1b0 [mlx5_core] mlx5e_rep_setup_tc_cb+0x153/0x750 [mlx5_core] tc_setup_cb_add+0x1dc/0x470 fl_change+0x2f4d/0x626d [cls_flower] tc_new_tfilter+0x79b/0x2310 rtnetlink_rcv_msg+0x778/0xad0 do_syscall_64+0x70/0x960 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Fixes: 04de7dda7394 ("net/mlx5e: Infrastructure for duplicated offloading of TC flows") Signed-off-by: Shay Drory Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260728044338.2271143-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 28cab4bf525c..7bfe7cdc5770 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -30,6 +30,7 @@ enum { MLX5E_TC_FLOW_FLAG_FAILED = MLX5E_TC_FLOW_BASE + 9, MLX5E_TC_FLOW_FLAG_SAMPLE = MLX5E_TC_FLOW_BASE + 10, MLX5E_TC_FLOW_FLAG_USE_ACT_STATS = MLX5E_TC_FLOW_BASE + 11, + MLX5E_TC_FLOW_FLAG_PEER = MLX5E_TC_FLOW_BASE + 12, }; struct mlx5e_tc_flow_parse_attr { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 1bc7b9019124..b290beb4369a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2161,7 +2161,8 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, if (mlx5e_is_eswitch_flow(flow)) { struct mlx5_devcom_comp_dev *devcom = flow->priv->mdev->priv.eswitch->devcom; - if (!mlx5_devcom_for_each_peer_begin(devcom)) { + if (flow_flag_test(flow, PEER) || + !mlx5_devcom_for_each_peer_begin(devcom)) { mlx5e_tc_del_fdb_flow(priv, flow); return; } @@ -4628,6 +4629,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, else in_mdev = priv->mdev; + flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_PEER); parse_attr = flow->attr->parse_attr; peer_flow = __mlx5e_add_fdb_flow(peer_priv, f, flow_flags, parse_attr->filter_dev, From cd09971dcc1c499ae0879010a00e9dba87abdc4f Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Mon, 27 Jul 2026 16:45:48 +0000 Subject: [PATCH 018/116] pds_core: keep the health thread stopped during reset Commit d9407ff11809 ("pds_core: Prevent health thread from running during reset/remove") stops the health thread with cancel_work_sync() before a reset, but a devcmd timeout during pdsc_fw_down() re-queues health_work, so pdsc_health_thread() runs again mid-reset and double allocates the core DMA queues via pdsc_fw_up(). Only the reset path is affected: on remove PDSC_S_STOPPING_DRIVER gates the health thread and the workqueue is destroyed. Use disable_work_sync() to cancel health_work and block further queue_work() on it, and enable_work() in pdsc_restart_health_thread() to re-allow it after the reset. disable_work_sync() keeps a disable depth, so every disable must be matched by one enable. pdsc_reset_prepare() stops the health thread and pdsc_reset_done() restarts it. On the AER path pdsc_pci_error_detected() calls pdsc_reset_prepare(), then pdsc_pci_error_resume() re-inits via pci_reset_function_locked() (pds_core has no .slot_reset handler), which runs the pair again - stopping the thread twice but restarting it once. Gate the disable and enable on a health_stopped flag so each fires at most once per stopped/running transition. Fixes: d9407ff11809 ("pds_core: Prevent health thread from running during reset/remove") Reported-by: sashiko-bot Closes: https://sashiko.dev/#/patchset/20260629200358.2626129-1-nikhil.rao%40amd.com?part=2 Signed-off-by: Nikhil P. Rao Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20260727164548.359562-1-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/core.h | 1 + drivers/net/ethernet/amd/pds_core/main.c | 10 ++++++++-- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index b7fe9ad73349..a1d41329209f 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -171,6 +171,7 @@ struct pdsc { struct timer_list wdtimer; unsigned int wdtimer_period; struct work_struct health_work; + bool health_stopped; struct devlink_health_reporter *fw_reporter; u32 fw_recoveries; diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index 8d94a4d70395..71a1d4b001c2 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -470,8 +470,10 @@ static void pdsc_stop_health_thread(struct pdsc *pdsc) return; timer_shutdown_sync(&pdsc->wdtimer); - if (pdsc->health_work.func) - cancel_work_sync(&pdsc->health_work); + if (pdsc->health_work.func && !pdsc->health_stopped) { + disable_work_sync(&pdsc->health_work); + pdsc->health_stopped = true; + } } static void pdsc_restart_health_thread(struct pdsc *pdsc) @@ -479,6 +481,10 @@ static void pdsc_restart_health_thread(struct pdsc *pdsc) if (pdsc->pdev->is_virtfn) return; + if (pdsc->health_stopped) { + enable_work(&pdsc->health_work); + pdsc->health_stopped = false; + } timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0); mod_timer(&pdsc->wdtimer, jiffies + 1); } From 57d635329d799b79096155cdf47ee0013d6780d1 Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Mon, 27 Jul 2026 17:00:30 +0000 Subject: [PATCH 019/116] pds_core: cancel pending PCI reset work on AER recovery pdsc_check_pci_health() queues pci_reset_work when it sees a broken PCI connection, and nothing cancels it. When the PCI core starts AER recovery, pdsc_pci_error_detected() runs pdsc_reset_prepare() and recovers the device, but a pci_reset_work queued just before is left pending. If it runs after recovery released the device lock, it resets a device the driver now considers healthy, bouncing the link for no reason. Cancel pci_reset_work in pdsc_pci_error_detected() after pdsc_reset_prepare(), which has already stopped the health thread so it cannot requeue the work. cancel_work_sync() is safe under the device lock here because pdsc_pci_reset_thread() uses pci_try_reset_function(), which returns instead of blocking on the lock. Only PFs initialize pci_reset_work, so guard the cancel with !is_virtfn. Fixes: 81665adf25d2 ("pds_core: Fix pdsc_check_pci_health function to use work thread") Reported-by: sashiko-bot Closes: https://sashiko.dev/#/patchset/20260714180223.1642792-2-nikhil.rao%40amd.com?part=1 Signed-off-by: Nikhil P. Rao Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20260727170030.361116-1-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index 71a1d4b001c2..9a2c64198d03 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -561,7 +561,11 @@ static pci_ers_result_t pdsc_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t error) { if (error == pci_channel_io_frozen) { + struct pdsc *pdsc = pci_get_drvdata(pdev); + pdsc_reset_prepare(pdev); + if (!pdev->is_virtfn) + cancel_work_sync(&pdsc->pci_reset_work); return PCI_ERS_RESULT_NEED_RESET; } From 2195424c3da2ef1829a63b807e3a900a90e57d85 Mon Sep 17 00:00:00 2001 From: Baul Lee Date: Mon, 27 Jul 2026 07:03:42 +0900 Subject: [PATCH 020/116] net/x25: fix use-after-free of the socket by its timers The x25 timers are armed with mod_timer() and cancelled with timer_delete(), so a pending timer holds no reference on the socket and a cancel does not wait for a callback already running on another CPU. x25_heartbeat_expiry() also rearms unconditionally, so it can reinstall sk->sk_timer after __x25_destroy_socket() has passed its cancel point. The following __sock_put() frees the socket while the timer is still queued, and the next expiry uses freed memory. KASAN reports a slab-use-after-free on the kmalloc-2k object freed by close(). timer_delete_sync() cannot be used here: x25_heartbeat_expiry() and x25_timer_expiry() both reach the cancels from inside the timer they would wait on, through __x25_destroy_socket() and x25_disconnect(). Arm the timers with sk_reset_timer() and cancel them with sk_stop_timer() so that an armed timer owns a reference, and release it in both expiry handlers. Rearm the heartbeat only while sk_hashed(sk) is still true, since __x25_destroy_socket() unlinks the socket before dropping it. Arm the deferred destroy timer the same way and drop its reference in x25_destroy_timer(). Reproduced on net with KASAN, with the heartbeat period shortened so the window recurs. With this patch the reproducer no longer triggers a report and /proc/net/x25 drains. Discovered by XBOW, triaged by Baul Lee Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Baul Lee Link: https://patch.msgid.link/20260726220342.47245-1-baul.lee@xbow.com Signed-off-by: Jakub Kicinski --- net/x25/af_x25.c | 4 ++-- net/x25/x25_timer.c | 25 ++++++++++++++++--------- 2 files changed, 18 insertions(+), 11 deletions(-) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 8aae9273b7c1..033e7d059f58 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -363,6 +363,7 @@ static void x25_destroy_timer(struct timer_list *t) struct sock *sk = timer_container_of(sk, t, sk_timer); x25_destroy_socket_from_timer(sk); + sock_put(sk); } /* @@ -398,9 +399,8 @@ static void __x25_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - sk->sk_timer.expires = jiffies + 10 * HZ; sk->sk_timer.function = x25_destroy_timer; - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 10 * HZ); } else { /* drop last reference so sock_put will free */ __sock_put(sk); diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c index 2ec63a1f4c6d..7896cd43f1cc 100644 --- a/net/x25/x25_timer.c +++ b/net/x25/x25_timer.c @@ -36,45 +36,45 @@ void x25_init_timers(struct sock *sk) void x25_start_heartbeat(struct sock *sk) { - mod_timer(&sk->sk_timer, jiffies + 5 * HZ); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ); } void x25_stop_heartbeat(struct sock *sk) { - timer_delete(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } void x25_start_t2timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t2); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t2); } void x25_start_t21timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t21); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t21); } void x25_start_t22timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t22); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t22); } void x25_start_t23timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t23); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t23); } void x25_stop_timer(struct sock *sk) { - timer_delete(&x25_sk(sk)->timer); + sk_stop_timer(sk, &x25_sk(sk)->timer); } unsigned long x25_display_timer(struct sock *sk) @@ -108,7 +108,7 @@ static void x25_heartbeat_expiry(struct timer_list *t) sock_flag(sk, SOCK_DEAD))) { bh_unlock_sock(sk); x25_destroy_socket_from_timer(sk); - return; + goto out; } break; @@ -120,8 +120,14 @@ static void x25_heartbeat_expiry(struct timer_list *t) break; } restart_heartbeat: - x25_start_heartbeat(sk); + /* Do not rearm once __x25_destroy_socket() has unlinked the socket: + * it is past its cancel point and owns the teardown from there on. + */ + if (sk_hashed(sk)) + x25_start_heartbeat(sk); bh_unlock_sock(sk); +out: + sock_put(sk); } /* @@ -166,4 +172,5 @@ static void x25_timer_expiry(struct timer_list *t) } else x25_do_timer_expiry(sk); bh_unlock_sock(sk); + sock_put(sk); } From 558f67f1340f803a346ecd14a69c49653111c5f4 Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Wed, 29 Jul 2026 21:56:59 +0800 Subject: [PATCH 021/116] ipvs: stop estimator after disabled calc phase IPVS estimator kthread 0 starts with zeroed chain and tick limits until its initial calculation phase completes. If network namespace teardown clears ipvs->enable during that phase, ip_vs_est_calc_phase() can return without installing positive limits. The kthread can then continue into its main loop and drain est_temp_list with zero chain_max, tick_max and est_max_count values. Each enqueue consumes one available tick row, but est_count never reaches the zero est_max_count value. After all rows are consumed, the row lookup returns IPVS_EST_NTICKS and ip_vs_enqueue_estimator() writes past the ticks and tick_len arrays. Exit kthread 0 after the calculation phase if the kthread is stopping or IPVS has been disabled. That keeps temporary estimators from being drained after the limits failed to initialize. Estimator kthreads can now self-exit before teardown or reload stops kd->task. Keep an extra task reference after creation and release it with kthread_stop_put(), so kd->task remains valid until the stop paths consume that reference. Fixes: 705dd3444081 ("ipvs: use kthreads for stats estimation") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zhiling Zou Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_est.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index ab09f5182951..05a216a47b45 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -191,8 +191,11 @@ static int ip_vs_estimation_kthread(void *data) } /* kthread 0 will handle the calc phase */ - if (ipvs->est_calc_phase) + if (ipvs->est_calc_phase) { ip_vs_est_calc_phase(ipvs); + if (kthread_should_stop() || !READ_ONCE(ipvs->enable)) + return 0; + } } while (1) { @@ -270,6 +273,7 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, kd->task = NULL; goto out; } + get_task_struct(kd->task); set_user_nice(kd->task, sysctl_est_nice(ipvs)); if (sysctl_est_preferred_cpulist(ipvs)) @@ -286,7 +290,7 @@ void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd) { if (kd->task) { pr_info("stopping estimator thread %d...\n", kd->id); - kthread_stop(kd->task); + kthread_stop_put(kd->task); kd->task = NULL; } } @@ -526,7 +530,7 @@ static void ip_vs_est_kthread_destroy(struct ip_vs_est_kt_data *kd) if (kd) { if (kd->task) { pr_info("stop unused estimator thread %d...\n", kd->id); - kthread_stop(kd->task); + kthread_stop_put(kd->task); } ip_vs_stats_free(kd->calc_stats); kfree(kd); From 30825970339c107bacaf7f61af90fcdb1f597ca1 Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Thu, 30 Jul 2026 01:31:00 +0800 Subject: [PATCH 022/116] netfilter: ebt_nflog: pin the NFLOG backend nf_log_unregister() runs after the per-net teardown so its final RCU grace period also drains readers that obtained the logger from a per-net binding. However, ebt_nflog passes an explicit ULOG log type to nf_log_packet() without holding a reference on the selected logger module, unlike the xt_NFLOG and nft_log frontends. An ebtables nflog rule can therefore remain callable while nfnetlink_log is unloaded. The resulting interleaving is: CPU 0 CPU 1 nfnetlink_log_fini() unregister_pernet_subsys() kfree(nfnl_log_pernet(net)) ebt_nflog_tg() nf_log_packet() nfulnl_log_packet() instance_lookup_get_rcu() The global ULOG logger is still registered at this point, so CPU 1 dereferences the per-net state after CPU 0 has freed it. KASAN reported: BUG: KASAN: slab-use-after-free in instance_lookup_get_rcu Read of size 8 at addr ff110001052e6210 by task poc/92 Call Trace: instance_lookup_get_rcu+0x1ce/0x1f0 [nfnetlink_log] nfulnl_log_packet+0x248/0x2fb0 [nfnetlink_log] nf_log_packet+0x204/0x300 ebt_nflog_tg+0x351/0x550 ebt_do_table+0xedf/0x22b0 Allocated by task 90: __kmalloc_noprof+0x186/0x470 ops_init+0x6d/0x420 register_pernet_operations+0x2f6/0x670 register_pernet_subsys+0x23/0x40 Freed by task 93: kfree+0x131/0x3c0 ops_undo_list+0x3e3/0x700 unregister_pernet_operations+0x232/0x490 unregister_pernet_subsys+0x1c/0x30 nfnetlink_log_fini+0x34/0x450 [nfnetlink_log] Acquire the ULOG logger module reference when an ebt_nflog rule is validated and release it when the rule is destroyed. Request the NFLOG backend for legacy callers when needed, matching xt_NFLOG. This prevents module teardown until all ebt_nflog rules have stopped using the logger. Fixes: c83fa19603bd ("netfilter: nf_log: don't call synchronize_rcu in nf_log_unset") Cc: stable@vger.kernel.org Signed-off-by: Chengfeng Ye Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebt_nflog.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c index 61bf8f4465ab..426f8adc912c 100644 --- a/net/bridge/netfilter/ebt_nflog.c +++ b/net/bridge/netfilter/ebt_nflog.c @@ -41,11 +41,25 @@ ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) static int ebt_nflog_tg_check(const struct xt_tgchk_param *par) { struct ebt_nflog_info *info = par->targinfo; + int ret; if (info->flags & ~EBT_NFLOG_MASK) return -EINVAL; info->prefix[EBT_NFLOG_PREFIX_SIZE - 1] = '\0'; - return 0; + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nfnetlink_log"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + } + + return ret; +} + +static void ebt_nflog_tg_destroy(const struct xt_tgdtor_param *par) +{ + nf_logger_put(par->family, NF_LOG_TYPE_ULOG); } static struct xt_target ebt_nflog_tg_reg __read_mostly = { @@ -54,6 +68,7 @@ static struct xt_target ebt_nflog_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_nflog_tg, .checkentry = ebt_nflog_tg_check, + .destroy = ebt_nflog_tg_destroy, .targetsize = sizeof(struct ebt_nflog_info), .me = THIS_MODULE, }; From 8e5fd2a55e2468f6225ef5af01ae58cdbcbae8cf Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 30 Jul 2026 20:38:49 +0200 Subject: [PATCH 023/116] netfilter: ipset: rework cidr bookkeeping According to sashiko, the current bookkeeping of cidr values are unsafe on weakly-ordered architectures. Replace the in-place updating with an RCU based method: create the new bookeeping structure, update and replace the old one with the new. Downside that we need to allocate memory when deleting a cidr entry - in case of memory pressure fall back to leave holes which possibility is taken into account at evaluation time. Thanks to Pablo (Pablo Neira Ayuso ) and Cyntia (Cynthia ) for helping me in debugging which resulted the patch "netfilter: ipset: allocate the proper memory for the generic hash structure" on which this very patch depends. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_hash_gen.h | 237 +++++++++++++------ net/netfilter/ipset/ip_set_hash_ipportnet.c | 4 +- net/netfilter/ipset/ip_set_hash_net.c | 4 +- net/netfilter/ipset/ip_set_hash_netiface.c | 4 +- net/netfilter/ipset/ip_set_hash_netnet.c | 12 +- net/netfilter/ipset/ip_set_hash_netport.c | 4 +- net/netfilter/ipset/ip_set_hash_netportnet.c | 12 +- 7 files changed, 183 insertions(+), 94 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index b2d77973272d..dd31992c915c 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -99,9 +99,15 @@ struct htable { #endif /* Book-keeping of the prefixes added to the set */ +struct net_prefix { + u8 cidr; /* the cidr value */ + u32 count; /* number of elements of this cidr */ +}; + struct net_prefixes { - u32 nets[IPSET_NET_COUNT]; /* number of elements for this cidr */ - u8 cidr[IPSET_NET_COUNT]; /* the cidr value */ + struct rcu_head rcu; + u8 len; + struct net_prefix nets[] __counted_by(len); }; /* Compute the hash table size */ @@ -127,11 +133,6 @@ htable_size(u8 hbits) #else #define __CIDR(cidr, i) (cidr) #endif - -/* cidr + 1 is stored in net_prefixes to support /0 */ -#define NCIDR_PUT(cidr) ((cidr) + 1) -#define NCIDR_GET(cidr) ((cidr) - 1) - #ifdef IP_SET_HASH_WITH_NETS_PACKED /* When cidr is packed with nomatch, cidr - 1 is stored in the data entry */ #define DCIDR_PUT(cidr) ((cidr) - 1) @@ -141,21 +142,11 @@ htable_size(u8 hbits) #define DCIDR_GET(cidr, i) __CIDR(cidr, i) #endif -#define INIT_CIDR(cidr, host_mask) \ - DCIDR_PUT(((cidr) ? NCIDR_GET(cidr) : host_mask)) +#define INIT_CIDR(n, host_mask) ({ \ + const struct net_prefixes *__n = rcu_dereference(n); \ + DCIDR_PUT((__n)->len ? (__n)->nets[0].cidr : host_mask);\ +}) -#ifdef IP_SET_HASH_WITH_NET0 -/* cidr from 0 to HOST_MASK value and c = cidr + 1 */ -#define NLEN (HOST_MASK + 1) -#define CIDR_POS(c) ((c) - 1) -#else -/* cidr from 1 to HOST_MASK value and c = cidr + 1 */ -#define NLEN HOST_MASK -#define CIDR_POS(c) ((c) - 2) -#endif - -#else -#define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ #define SET_ELEM_EXPIRED(set, d) \ @@ -292,6 +283,7 @@ static const union nf_inet_addr zeromask = {}; /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ + struct net_prefixes __rcu *rnets[IPSET_NET_COUNT]; /* cidr prefixes */ struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ @@ -302,9 +294,6 @@ struct htype { #if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) u8 netmask; /* netmask value for subnets to store */ union nf_inet_addr bitmask; /* stores bitmask */ -#endif -#ifdef IP_SET_HASH_WITH_NETS - struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif /* Because 'next' is IPv4/IPv6 dependent, no elements of this * structure and referred in create() may come after 'next'. @@ -326,50 +315,92 @@ struct mtype_resize_ad { /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ -static void +static int mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { - int i, j; + struct net_prefixes *nets, *tmp; + int i, j, found, len = 0, ret = 0; spin_lock_bh(&set->lock); + nets = __ipset_dereference(h->rnets[n]); /* Add in increasing prefix order, so larger cidr first */ - for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { - if (j != -1) { + for (i = 0, found = -1; i < nets->len; i++) { + if (nets->nets[i].count) + len++; + if (found != -1) { continue; - } else if (h->nets[i].cidr[n] < cidr) { - j = i; - } else if (h->nets[i].cidr[n] == cidr) { - h->nets[CIDR_POS(cidr)].nets[n]++; + } else if (nets->nets[i].cidr < cidr) { + found = i; + } else if (nets->nets[i].cidr == cidr) { + nets->nets[i].count++; goto unlock; } } - if (j != -1) { - for (; i > j; i--) - h->nets[i].cidr[n] = h->nets[i - 1].cidr[n]; + len++; + tmp = kzalloc_flex(*tmp, nets, len, GFP_ATOMIC); + if (!tmp) { + ret = -ENOMEM; + goto unlock; } - h->nets[i].cidr[n] = cidr; - h->nets[CIDR_POS(cidr)].nets[n] = 1; + + tmp->len = len; + for (i = 0, j = 0; i < nets->len; i++) { + if (i == found) { + tmp->nets[j].cidr = cidr; + tmp->nets[j++].count = 1; + } + if (!nets->nets[i].count) + continue; + tmp->nets[j].cidr = nets->nets[i].cidr; + tmp->nets[j++].count = nets->nets[i].count; + } + if (found == -1) { + tmp->nets[j].cidr = cidr; + tmp->nets[j].count = 1; + } + rcu_assign_pointer(h->rnets[n], tmp); + kfree_rcu(nets, rcu); unlock: spin_unlock_bh(&set->lock); + return ret; } static void mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { - u8 i, j, net_end = NLEN - 1; + struct net_prefixes *nets, *tmp; + u8 i, j, len = 0; + int found; spin_lock_bh(&set->lock); - for (i = 0; i < NLEN; i++) { - if (h->nets[i].cidr[n] != cidr) - continue; - h->nets[CIDR_POS(cidr)].nets[n]--; - if (h->nets[CIDR_POS(cidr)].nets[n] > 0) - goto unlock; - for (j = i; j < net_end && h->nets[j].cidr[n]; j++) - h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; - h->nets[j].cidr[n] = 0; - goto unlock; + nets = __ipset_dereference(h->rnets[n]); + for (i = 0, found = -1; i < nets->len; i++) { + if (nets->nets[i].count) + len++; + if (nets->nets[i].cidr == cidr) + found = i; } + if (unlikely(found == -1)) + goto unlock; + + nets->nets[found].count--; + if (nets->nets[found].count) + goto unlock; + len--; + tmp = kzalloc_flex(*tmp, nets, len, GFP_ATOMIC); + if (!tmp) + /* Leave a hole */ + goto unlock; + + tmp->len = len; + for (i = 0, j = 0; i < nets->len; i++) { + if (!nets->nets[i].count || i == found) + continue; + tmp->nets[j].cidr = nets->nets[i].cidr; + tmp->nets[j++].count = nets->nets[i].count; + } + rcu_assign_pointer(h->rnets[n], tmp); + kfree_rcu(nets, rcu); unlock: spin_unlock_bh(&set->lock); } @@ -402,6 +433,9 @@ static void mtype_flush(struct ip_set *set) { struct htype *h = set->data; +#ifdef IP_SET_HASH_WITH_NETS + struct net_prefixes *nets, *tmp; +#endif struct htable *t; struct hbucket *n; u32 r, i; @@ -425,7 +459,19 @@ mtype_flush(struct ip_set *set) spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS - memset(h->nets, 0, sizeof(h->nets)); + for (i = 0; i < IPSET_NET_COUNT; i++) { + nets = ipset_dereference_nfnl(h->rnets[i]); + tmp = kzalloc_obj(*tmp, GFP_ATOMIC); + if (!tmp) { + u8 j; + + for (j = 0; j < nets->len; j++) + nets->nets[j].count = 0; + } else { + rcu_assign_pointer(h->rnets[i], tmp); + kfree_rcu(nets, rcu); + } + } #endif } @@ -433,6 +479,9 @@ mtype_flush(struct ip_set *set) static void mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) { +#ifdef IP_SET_HASH_WITH_NETS + struct htype *h = set->data; +#endif struct hbucket *n; u32 i; @@ -446,6 +495,11 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) kfree(n); } +#ifdef IP_SET_HASH_WITH_NETS + if (ext_destroy) + for (i = 0; i < IPSET_NET_COUNT; i++) + kfree(rcu_dereference_raw(h->rnets[i])); +#endif ip_set_free(t->hregion); ip_set_free(t); } @@ -519,8 +573,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) mtype_del_cidr(set, h, - NCIDR_PUT(DCIDR_GET(data->cidr, k)), - k); + DCIDR_GET(data->cidr, k), k); #endif t->hregion[r].elements--; ip_set_ext_destroy(set, data); @@ -950,8 +1003,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) mtype_del_cidr(set, h, - NCIDR_PUT(DCIDR_GET(data->cidr, i)), - i); + DCIDR_GET(data->cidr, i), i); #endif ip_set_ext_destroy(set, data); t->hregion[r].elements--; @@ -996,7 +1048,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); + mtype_add_cidr(set, h, DCIDR_GET(d->cidr, i), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: @@ -1110,7 +1162,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) mtype_del_cidr(set, h, - NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); + DCIDR_GET(d->cidr, j), j); #endif ip_set_ext_destroy(set, data); @@ -1193,28 +1245,37 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, { struct htype *h = set->data; struct htable *t = rcu_dereference_bh(h->table); + struct net_prefixes *nets0; struct hbucket *n; struct mtype_elem *data; #if IPSET_NET_COUNT == 2 + struct net_prefixes *nets1; struct mtype_elem orig = *d; - int ret, i, j = 0, k; + int ret, i, j, k; #else - int ret, i, j = 0; + int ret, i, j; #endif u32 key, multi = 0; u8 pos; pr_debug("test by nets\n"); - for (; j < NLEN && h->nets[j].cidr[0] && !multi; j++) { + rcu_read_lock_bh(); + nets0 = rcu_dereference_bh(h->rnets[0]); +#if IPSET_NET_COUNT == 2 + nets1 = rcu_dereference_bh(h->rnets[1]); +#endif + for (j = 0; j < nets0->len && !multi; j++) { + if (!nets0->nets[j].count) + continue; #if IPSET_NET_COUNT == 2 mtype_data_reset_elem(d, &orig); - mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0]), false); - for (k = 0; k < NLEN && h->nets[k].cidr[1] && !multi; - k++) { - mtype_data_netmask(d, NCIDR_GET(h->nets[k].cidr[1]), - true); + mtype_data_netmask(d, nets0->nets[j].cidr, false); + for (k = 0; k < nets1->len && !multi; k++) { + if (!nets1->nets[k].count) + continue; + mtype_data_netmask(d, nets1->nets[k].cidr, true); #else - mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0])); + mtype_data_netmask(d, nets0->nets[j].cidr); #endif key = HKEY(d, h->initval, t->htable_bits); n = rcu_dereference_bh(hbucket(t, key)); @@ -1229,7 +1290,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, continue; ret = mtype_data_match(data, ext, mext, set, flags); if (ret != 0) - return ret; + goto unlock; #ifdef IP_SET_HASH_WITH_MULTI /* No match, reset multiple match flag */ multi = 0; @@ -1239,7 +1300,10 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, } #endif } - return 0; + ret = 0; +unlock: + rcu_read_unlock_bh(); + return ret; } #endif @@ -1504,6 +1568,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, int ret __attribute__((unused)) = 0; u8 netmask = set->family == NFPROTO_IPV4 ? 32 : 128; union nf_inet_addr bitmask = onesmask; +#endif +#ifdef IP_SET_HASH_WITH_NETS + struct net_prefixes *nets; #endif size_t hsize; struct htype *h; @@ -1604,21 +1671,25 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, */ hbits = fls(hashsize - 1); hsize = htable_size(hbits); - if (hsize == 0) { - kfree(h); - return -ENOMEM; - } + if (hsize == 0) + goto free_h; t = ip_set_alloc(hsize); - if (!t) { - kfree(h); - return -ENOMEM; - } + if (!t) + goto free_h; t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); - if (!t->hregion) { - ip_set_free(t); - kfree(h); - return -ENOMEM; + if (!t->hregion) + goto free_t; +#ifdef IP_SET_HASH_WITH_NETS + for (i = 0; i < IPSET_NET_COUNT; i++) { + nets = kzalloc_obj(*nets); + if (!nets) { + while (i > 0) + kfree(rcu_dereference_raw(h->rnets[--i])); + goto free_hregion; + } + RCU_INIT_POINTER(h->rnets[i], nets); } +#endif h->gc.set = set; spin_lock_init(&h->gc.lock); for (i = 0; i < ahash_numof_locks(hbits); i++) @@ -1682,6 +1753,16 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, t->htable_bits, h->maxelem, set->data, t); return 0; + +#ifdef IP_SET_HASH_WITH_NETS +free_hregion: + ip_set_free(t->hregion); +#endif +free_t: + ip_set_free(t); +free_h: + kfree(h); + return -ENOMEM; } #endif /* IP_SET_EMIT_CREATE */ diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 2d6652d43199..195853a25b06 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -138,7 +138,7 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_ipportnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -398,7 +398,7 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_ipportnet6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet6_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index ce0a9ce5a91f..092f3c9281b8 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -117,7 +117,7 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_net4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -291,7 +291,7 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_net6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net6_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 30a655e5c4fd..b44b95f766b7 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -161,7 +161,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netiface4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), .elem = 1, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -382,7 +382,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netiface6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface6_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), .elem = 1, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 8fbe649c9dd3..f7c8a1cc30fc 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -149,8 +149,10 @@ hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + rcu_read_lock_bh(); + e.cidr[0] = INIT_CIDR(h->rnets[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->rnets[1], HOST_MASK); + rcu_read_unlock_bh(); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK; @@ -388,8 +390,10 @@ hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + rcu_read_lock_bh(); + e.cidr[0] = INIT_CIDR(h->rnets[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->rnets[1], HOST_MASK); + rcu_read_unlock_bh(); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK; diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index d1a0628df4ef..5de4b511de76 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -133,7 +133,7 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -353,7 +353,7 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_netport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index bf4f91b78e1d..6291532be7a5 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -157,8 +157,10 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + rcu_read_lock_bh(); + e.cidr[0] = INIT_CIDR(h->rnets[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->rnets[1], HOST_MASK); + rcu_read_unlock_bh(); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK; @@ -452,8 +454,10 @@ hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netportnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + rcu_read_lock_bh(); + e.cidr[0] = INIT_CIDR(h->rnets[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->rnets[1], HOST_MASK); + rcu_read_unlock_bh(); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK; From 712a6f545c359b427daa9a5a782e30d2f8331e25 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 30 Jul 2026 20:38:50 +0200 Subject: [PATCH 024/116] netfilter: ipset: switch ext_size to atomic64_t The hash types do not acquire set->lock, they use 'region locking' where only part of the hash table is locked. Parallel inserts and deletes are possible and CPUs can race on ->ext_size update. Switch to atomic64_t. This leaves another bug unresolved: there still can be a race on comment extension re-init. This will be handled in a later commit when converting to rhashtable backend. Fixes: f66ee0410b1c ("netfilter: ipset: Fix "INFO: rcu detected stall in hash_xxx" reports") Signed-off-by: Jozsef Kadlecsik Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 2 +- net/netfilter/ipset/ip_set_bitmap_gen.h | 4 ++-- net/netfilter/ipset/ip_set_core.c | 6 +++--- net/netfilter/ipset/ip_set_hash_gen.h | 2 +- net/netfilter/ipset/ip_set_list_set.c | 4 ++-- 5 files changed, 9 insertions(+), 9 deletions(-) diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index b98331572ad2..cadae9b2578f 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -273,7 +273,7 @@ struct ip_set { /* Number of elements (vs timeout) */ u32 elements; /* Size of the dynamic extensions (vs timeout) */ - size_t ext_size; + atomic64_t ext_size; /* Element data size */ size_t dsize; /* Offsets to extensions in elements */ diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index bb9b5bed10e1..226fdf17b683 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -77,7 +77,7 @@ mtype_flush(struct ip_set *set) mtype_ext_cleanup(set); bitmap_zero(map->members, map->elements); set->elements = 0; - set->ext_size = 0; + atomic64_set(&set->ext_size, 0); } /* Calculate the actual memory size of the set data */ @@ -93,7 +93,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) { const struct mtype *map = set->data; struct nlattr *nested; - size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size; + size_t memsize = mtype_memsize(map, set->dsize) + atomic64_read(&set->ext_size); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 6cfad152d7d1..822a53a7f502 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -350,7 +350,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, size_t len = ext->comment ? strlen(ext->comment) : 0; if (unlikely(c)) { - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, NULL); kfree_rcu(c, rcu); } @@ -362,7 +362,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, if (unlikely(!c)) return; strscpy(c->str, ext->comment, len + 1); - set->ext_size += sizeof(*c) + strlen(c->str) + 1; + atomic64_add(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, c); } EXPORT_SYMBOL_GPL(ip_set_init_comment); @@ -392,7 +392,7 @@ ip_set_comment_free(struct ip_set *set, void *ptr) c = rcu_dereference_protected(comment->c, 1); if (unlikely(!c)) return; - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, NULL); kfree_rcu(c, rcu); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index dd31992c915c..8841daf28f01 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1373,7 +1373,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); mtype_ext_size(set, &elements, &ext_size); - memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; + memsize = mtype_ahash_memsize(h, t) + ext_size + atomic64_read(&set->ext_size); htable_bits = t->htable_bits; rcu_read_unlock_bh(); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 1cef84f15e8c..ca3ef9479e83 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -421,7 +421,7 @@ list_set_flush(struct ip_set *set) list_for_each_entry_safe(e, n, &map->members, list) list_set_del(set, e); set->elements = 0; - set->ext_size = 0; + atomic64_set(&set->ext_size, 0); } static void @@ -455,7 +455,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) { const struct list_set *map = set->data; struct nlattr *nested; - size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size; + size_t memsize = list_set_memsize(map, set->dsize) + atomic64_read(&set->ext_size); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) From c266769e9ede96b95f9cffc90274da1e25f7a74e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 30 Jul 2026 20:38:51 +0200 Subject: [PATCH 025/116] netfilter: ipset: add small wrappers for hash and bucket sizes Preparation patch. Once the ipset hash table is replaced with rhashtable these functions are needed. Add them in extra commit to have reviewable chunks. Assisted-by: Claude:claude-sonnet-4-6 Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_hash_gen.h | 39 +++++++++++++++++++++------ 1 file changed, 31 insertions(+), 8 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 8841daf28f01..ef586b486f51 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -201,6 +201,8 @@ static const union nf_inet_addr zeromask = {}; #undef mtype_same_set #undef mtype_kadt #undef mtype_uadt +#undef mtype_bucket_size +#undef mtype_hash_size #undef mtype_add #undef mtype_del @@ -246,6 +248,8 @@ static const union nf_inet_addr zeromask = {}; #define mtype_same_set IPSET_TOKEN(MTYPE, _same_set) #define mtype_kadt IPSET_TOKEN(MTYPE, _kadt) #define mtype_uadt IPSET_TOKEN(MTYPE, _uadt) +#define mtype_bucket_size IPSET_TOKEN(MTYPE, _bucket_size) +#define mtype_hash_size IPSET_TOKEN(MTYPE, _hash_size) #define mtype_add IPSET_TOKEN(MTYPE, _add) #define mtype_del IPSET_TOKEN(MTYPE, _del) @@ -1358,6 +1362,24 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, return ret; } +static u32 mtype_hash_size(const struct htype *h) +{ + const struct htable *t; + u8 htable_bits; + + rcu_read_lock(); + t = rcu_dereference(h->table); + htable_bits = t->htable_bits; + rcu_read_unlock(); + + return jhash_size(htable_bits); +} + +static u32 mtype_bucket_size(const struct htype *h) +{ + return h->bucketsize; +} + /* Reply a HEADER request: fill out the header part of the set */ static int mtype_head(struct ip_set *set, struct sk_buff *skb) @@ -1368,21 +1390,20 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) size_t memsize; u32 elements = 0; size_t ext_size = 0; - u8 htable_bits; rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); mtype_ext_size(set, &elements, &ext_size); memsize = mtype_ahash_memsize(h, t) + ext_size + atomic64_read(&set->ext_size); - htable_bits = t->htable_bits; rcu_read_unlock_bh(); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, - htonl(jhash_size(htable_bits))) || - nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) + + if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, htonl(mtype_hash_size(h)))) + goto nla_put_failure; + if (nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) goto nla_put_failure; #ifdef IP_SET_HASH_WITH_BITMASK /* if netmask is set to anything other than HOST_MASK we know that the user supplied netmask @@ -1406,8 +1427,9 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; #endif if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) { - if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) || - nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval))) + if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, mtype_bucket_size(h))) + goto nla_put_failure; + if (nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval))) goto nla_put_failure; } if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || @@ -1721,6 +1743,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, INIT_LIST_HEAD(&t->ad); RCU_INIT_POINTER(h->table, t); set->data = h; + #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { #endif @@ -1749,7 +1772,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", - set->name, jhash_size(t->htable_bits), + set->name, mtype_hash_size(h), t->htable_bits, h->maxelem, set->data, t); return 0; From cdd97fae0e96fc0f78418b93ca864f98cd63e99a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 30 Jul 2026 20:38:52 +0200 Subject: [PATCH 026/116] netfilter: ipset: add and use mtype_del_cidr_all helper Reduces size of upcoming rhashtable conversion. Assisted-by: Claude:claude-sonnet-4-6 Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_hash_gen.h | 34 +++++++++++++-------------- 1 file changed, 16 insertions(+), 18 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index ef586b486f51..f00c82acd7f0 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -195,6 +195,7 @@ static const union nf_inet_addr zeromask = {}; #undef mtype_ext_cleanup #undef mtype_add_cidr #undef mtype_del_cidr +#undef mtype_del_cidr_all #undef mtype_ahash_memsize #undef mtype_flush #undef mtype_destroy @@ -242,6 +243,7 @@ static const union nf_inet_addr zeromask = {}; #define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup) #define mtype_add_cidr IPSET_TOKEN(MTYPE, _add_cidr) #define mtype_del_cidr IPSET_TOKEN(MTYPE, _del_cidr) +#define mtype_del_cidr_all IPSET_TOKEN(MTYPE, _del_cidr_all) #define mtype_ahash_memsize IPSET_TOKEN(MTYPE, _ahash_memsize) #define mtype_flush IPSET_TOKEN(MTYPE, _flush) #define mtype_destroy IPSET_TOKEN(MTYPE, _destroy) @@ -410,6 +412,17 @@ mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) } #endif +static void +mtype_del_cidr_all(struct ip_set *set, struct htype *h, const struct mtype_elem *data) +{ +#ifdef IP_SET_HASH_WITH_NETS + int k; + + for (k = 0; k < IPSET_NET_COUNT; k++) + mtype_del_cidr(set, h, DCIDR_GET(data->cidr, k), k); +#endif +} + /* Calculate the actual memory size of the set data */ static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) @@ -551,9 +564,6 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) struct mtype_elem *data; u32 i, j, d; size_t dsize = set->dsize; -#ifdef IP_SET_HASH_WITH_NETS - u8 k; -#endif u8 pos, htable_bits = t->htable_bits; spin_lock_bh(&t->hregion[r].lock); @@ -574,11 +584,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) pr_debug("expired %u/%u\n", i, j); clear_bit(j, n->used); smp_mb__after_atomic(); -#ifdef IP_SET_HASH_WITH_NETS - for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(set, h, - DCIDR_GET(data->cidr, k), k); -#endif + mtype_del_cidr_all(set, h, data); t->hregion[r].elements--; ip_set_ext_destroy(set, data); d++; @@ -1004,11 +1010,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { -#ifdef IP_SET_HASH_WITH_NETS - for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_del_cidr(set, h, - DCIDR_GET(data->cidr, i), i); -#endif + mtype_del_cidr_all(set, h, data); ip_set_ext_destroy(set, data); t->hregion[r].elements--; } @@ -1163,11 +1165,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (i + 1 == pos) smp_store_release(&n->pos, --pos); t->hregion[r].elements--; -#ifdef IP_SET_HASH_WITH_NETS - for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(set, h, - DCIDR_GET(d->cidr, j), j); -#endif + mtype_del_cidr_all(set, h, d); ip_set_ext_destroy(set, data); if (t->resizing && ext && ext->target) { From 7defddefa95b3699b05b23bf3ceea94d872509bb Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 30 Jul 2026 20:38:53 +0200 Subject: [PATCH 027/116] netfilter: ipset: switch to rcu work In the initial ipset rhashtable conversion RFC series syzbot reported following splat: BUG: sleeping function [..] at kernel/irq_work.c:289 in_atomic(): 1, [..] irq_work_sync.. kernel/irq_work.c:289 rhashtable_free_and_destroy.. lib/rhashtable.c:1295 hash_netport4_destroy.. net/netfilter/ipset/ip_set_hash_gen.h:420 ip_set_destroy_set_rcu.. net/netfilter/ipset/ip_set_core.c:1169 rcu_core.. kernel/rcu/tree.c:2897 This is because post-rhashtable-conversion hash implementation needs to schedule in the destroy callback. At this time this isn't allowed. Replace existing call_rcu() based destruction with rcu_work api. Also allows to undo split of set destruction and gc work cancelling in a future patch. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 4 +-- net/netfilter/ipset/ip_set_core.c | 46 ++++++++++++++++---------- 2 files changed, 31 insertions(+), 19 deletions(-) diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index cadae9b2578f..c46864cc6623 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -244,8 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { - /* For call_cru in destroy */ - struct rcu_head rcu; + /* for set destruction */ + struct rcu_work rwork; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 822a53a7f502..543851a923d0 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -25,6 +25,7 @@ static LIST_HEAD(ip_set_type_list); /* all registered set types */ static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */ static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */ +static struct workqueue_struct *ipset_destroy_wq; struct ip_set_net { struct ip_set * __rcu *ip_set_list; /* all individual sets */ @@ -1178,22 +1179,26 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { .len = IPSET_MAXNAMELEN - 1 }, }; -/* In order to return quickly when destroying a single set, it is split - * into two stages: - * - Cancel garbage collector - * - Destroy the set itself via call_rcu() - */ - static void -ip_set_destroy_set_rcu(struct rcu_head *head) +destroy_and_free_set(struct ip_set *set) { - struct ip_set *set = container_of(head, struct ip_set, rcu); - set->variant->destroy(set); module_put(set->type->me); kfree(set); } +/* In order to return quickly when destroying a single set, + * destruction is done asynchronously via work queues. + */ +static void +ip_set_destroy_set_work(struct work_struct *work) +{ + struct ip_set *set = container_of(to_rcu_work(work), + struct ip_set, rwork); + + destroy_and_free_set(set); +} + static void _destroy_all_sets(struct ip_set_net *inst) { @@ -1283,7 +1288,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, /* Must wait for flush to be really finished */ rcu_barrier(); } - call_rcu(&s->rcu, ip_set_destroy_set_rcu); + INIT_RCU_WORK(&s->rwork, ip_set_destroy_set_work); + queue_rcu_work(ipset_destroy_wq, &s->rwork); } return 0; out: @@ -2421,18 +2427,23 @@ static struct pernet_operations ip_set_net_ops = { static int __init ip_set_init(void) { - int ret = register_pernet_subsys(&ip_set_net_ops); + int ret; + ipset_destroy_wq = alloc_ordered_workqueue("ipset_destroy_wq", 0); + if (!ipset_destroy_wq) + return -ENOMEM; + + ret = register_pernet_subsys(&ip_set_net_ops); if (ret) { pr_err("ip_set: cannot register pernet_subsys.\n"); - return ret; + goto out_wq; } ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); if (ret != 0) { pr_err("ip_set: cannot register with nfnetlink.\n"); unregister_pernet_subsys(&ip_set_net_ops); - return ret; + goto out_wq; } ret = nf_register_sockopt(&so_set); @@ -2440,10 +2451,13 @@ ip_set_init(void) pr_err("SO_SET registry failed: %d\n", ret); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); unregister_pernet_subsys(&ip_set_net_ops); - return ret; + goto out_wq; } return 0; +out_wq: + destroy_workqueue(ipset_destroy_wq); + return ret; } static void __exit @@ -2453,9 +2467,7 @@ ip_set_fini(void) nfnetlink_subsys_unregister(&ip_set_netlink_subsys); unregister_pernet_subsys(&ip_set_net_ops); - /* Wait for call_rcu() in destroy */ - rcu_barrier(); - + destroy_workqueue(ipset_destroy_wq); pr_debug("these are the famous last words\n"); } From 646922a0379496154e8c8faca4f8e2fd9100cacc Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 30 Jul 2026 21:35:05 +0300 Subject: [PATCH 028/116] ipvs: avoid out-of-bounds write in ip_vs_nat_icmp Sashiko warns that local attacker can modify the packet while it is processed by IPVS. Some places read the IP ihl field multiple times which can cause out-of-bounds access. One such place is ip_vs_nat_icmp where we can write after the validated area. Fix it by providing ciph argument just like it is done for IPv6 and use ciph->len as offset to the embedded transport header. Modify some IPv4 header checks by reading the ihl field only once. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://sashiko.dev/#/patchset/20260722101517.36313-1-ja%40ssi.bg Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 69 +++++++++++++++++---------------- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- 3 files changed, 37 insertions(+), 36 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index e6ca930a3507..1235f1934e94 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -2062,7 +2062,7 @@ static inline bool ip_vs_conn_use_hash2(struct ip_vs_conn *cp) void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int dir, unsigned int toff, - bool has_ports); + bool has_ports, struct ip_vs_iphdr *ciph); #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 6b79e0c4d9e2..0bdaeb4ed61e 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -925,28 +925,27 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout, unsigned int toff, - bool has_ports) + bool has_ports, struct ip_vs_iphdr *ciph) { struct iphdr *iph = ip_hdr(skb); struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); - struct iphdr *ciph = (struct iphdr *)(icmph + 1); - unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr); + struct iphdr *cih = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); - ciph->daddr = cp->vaddr.ip; - ip_send_check(ciph); + cih->daddr = cp->vaddr.ip; + ip_send_check(cih); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); - ciph->saddr = cp->daddr.ip; - ip_send_check(ciph); + cih->saddr = cp->daddr.ip; + ip_send_check(cih); } /* the TCP/UDP/SCTP port */ if (has_ports) { - __be16 *ports = (void *)ciph + ciph->ihl*4; + __be16 *ports = (void *)(skb->data + ciph->len); if (inout) ports[1] = cp->vport; @@ -960,10 +959,10 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) - IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered outgoing ICMP"); else - IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered incoming ICMP"); } @@ -1056,7 +1055,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports); + ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -1092,7 +1091,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; - unsigned int offset, ihl; + unsigned int offset; union nf_inet_addr snet; *related = 1; @@ -1105,7 +1104,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; } - ihl = ipvsh->len; offset = ipvsh->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) @@ -1131,11 +1129,15 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, /* Now find the contained IP header */ offset += sizeof(_icmph); - cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) + if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ - pp = ip_vs_proto_get(cih->protocol); + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); + if (!(cih && cih->version == 4 && + ciph.len - ciph.off >= sizeof(struct iphdr))) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + + pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; @@ -1146,8 +1148,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); - ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); - /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); @@ -1155,8 +1155,8 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; snet.ip = ipvsh->saddr.ip; - return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl, - hooknum); + return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, + ipvsh->len, hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -1803,10 +1803,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) + if (!cih) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + hlen_ipip = cih->ihl * 4; + if (!(cih->version == 4 && hlen_ipip >= sizeof(struct iphdr))) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; - hlen_ipip = cih->ihl * 4; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; @@ -1823,9 +1825,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += hlen_ipip; - cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) - return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ @@ -1850,21 +1849,25 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ - cih = skb_header_pointer(skb, offset, sizeof(_ciph), - &_ciph); - if (cih && cih->version == 4 && cih->ihl >= 5 && - iproto == IPPROTO_IPIP) + if (iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } - pd = ip_vs_proto_data_get(ipvs, cih->protocol); + if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph)) + return NF_ACCEPT; + pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); + if (!(cih && cih->version == 4 && + ciph.len - ciph.off >= sizeof(struct iphdr))) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; @@ -1872,9 +1875,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); - offset2 = offset; - ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); - /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ @@ -1904,11 +1904,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, } if (tunnel) { - unsigned int hlen_orig = cih->ihl * 4; + unsigned int hlen_orig = ciph.len - ciph.off; __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; + offset2 = offset; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 0b0c5304993a..c4508f3f43dd 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1580,7 +1580,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports); + ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; From 99609cb0aa789c8d071050ce8579989551882cc6 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 30 Jul 2026 21:35:06 +0300 Subject: [PATCH 029/116] ipvs: return the csum validation for forward hook Sashiko notes that playing games with the skb dst and rt flags instead of providing hooknum is not a good idea when validating the checksums. Also, skipping checksum validation for FORWARD packets risk silent data corruption, even if the only user is the FTP-CMD packets coming from the real server. Sashiko also noticed that by using common checksum helper in the previous commit we actually fixed old bug where the TCP/UDP checksum for IPv6 on CHECKSUM_COMPLETE was not validated correctly. Fixes: e876b75b9020 ("ipvs: fix the checksum validations") Link: https://sashiko.dev/#/patchset/20260722211420.153933-1-pablo%40netfilter.org Link: https://sashiko.dev/#/patchset/20260727185024.67534-1-ja%40ssi.bg Link: https://sashiko.dev/#/patchset/20260728202520.59179-1-ja%40ssi.bg Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 19 +++++-------------- net/netfilter/ipvs/ip_vs_proto_sctp.c | 2 +- 2 files changed, 6 insertions(+), 15 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 1235f1934e94..d2813eb795be 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,9 +25,7 @@ #include /* for union nf_inet_addr */ #include #include /* for struct ipv6hdr */ -#include #include -#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif @@ -2095,30 +2093,23 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } -static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af) +static inline bool ip_vs_checksum_needed(struct sk_buff *skb) { /* Checksum unnecessary or already validated? */ if (skb_csum_unnecessary(skb)) return false; - /* LOCAL_OUT ? */ - if (!skb->dev || skb->dev->flags & IFF_LOOPBACK) + /* Locally generated ? */ + if (!skb->dev) return false; - /* !LOCAL_IN (FORWARD) ? */ - if (af == AF_INET6) { - if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL)) - return false; - } else { - if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) - return false; - } return true; } static inline bool ip_vs_checksum_common_check(struct sk_buff *skb, int offset, int proto, int af) { - if (!ip_vs_checksum_needed(skb, af)) + if (!ip_vs_checksum_needed(skb)) return true; + /* Validate csum even for FORWARD */ return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af); } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 3dbd3096e163..c80567c73469 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -193,7 +193,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, struct sctphdr *sh; __le32 cmp, val; - if (!ip_vs_checksum_needed(skb, af)) + if (!ip_vs_checksum_needed(skb)) return 1; sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; From 976245094925bab9bc39366b2e9ab44ffcde61d0 Mon Sep 17 00:00:00 2001 From: Mahanta Jambigi Date: Wed, 29 Jul 2026 15:01:53 +0200 Subject: [PATCH 030/116] net/smc: fix qentry overwrite for CONFIRM_LINK and ADD_LINK_CONT in smc_llc_event_handler() The SMC_LLC_CONFIRM_LINK / SMC_LLC_ADD_LINK_CONT branch in smc_llc_event_handler() stores an incoming qentry into the local LLC flow without first checking whether a qentry is already pending. If a malicious or buggy peer sends a second CONFIRM_LINK or ADD_LINK_CONT request while a flow is active and flow->qentry is already set, smc_llc_flow_qentry_set() overwrites the pointer without freeing the previous allocation, leaking one kmalloc-96 object per spurious message. The sibling SMC_LLC_DELETE_LINK branch already has the correct !flow->qentry guard. Apply the same guard to the CONFIRM_LINK/ADD_LINK_CONT branch so that a duplicate message when qentry is already occupied falls through to break and is freed by the kfree(qentry) at the out: label, rather than silently leaking the existing allocation. The response direction (smc_llc_rx_response()) is unaffected: it already guards with flow->qentry at the equivalent site and drops duplicate responses correctly. Fixes: 0fb0b02bd6fd ("net/smc: adapt SMC client code to use the LLC flow") Signed-off-by: Mahanta Jambigi Reviewed-by: Hidayath Khan Reviewed-by: Sidraya Jayagond Reviewed-by: Dust Li Link: https://patch.msgid.link/20260729130153.970800-1-mjambigi@linux.ibm.com Signed-off-by: Jakub Kicinski --- net/smc/smc_llc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 954b2ff1815c..aa6d83af55ed 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -1927,7 +1927,8 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) return; case SMC_LLC_CONFIRM_LINK: case SMC_LLC_ADD_LINK_CONT: - if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { + if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE && + !lgr->llc_flow_lcl.qentry) { /* a flow is waiting for this message */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); wake_up(&lgr->llc_msg_waiter); From 63488dba65ef91373ef616575b32eb0eb21459f4 Mon Sep 17 00:00:00 2001 From: Baul Lee Date: Wed, 29 Jul 2026 22:19:41 +0900 Subject: [PATCH 031/116] net: bridge: mrp: fix uninitialised bytes on the wire br_mrp_alloc_test_skb() builds MRP test frames on an skb from dev_alloc_skb(), which does not clear the linear data area. On the MRA ring-role branch the sub-option TLV header is appended with sub_tlv = skb_put(skb, sizeof(*sub_tlv)); sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; so sub_tlv->length is never written, and the two trailing alignment bytes are appended with a bare skb_put() that does not clear them either. The neighbouring oui and sub_opt regions are explicitly zeroed, so three uninitialised bytes are left in every MRA MRP_Test frame that goes out. Put the sub-option TLV header and the alignment padding in a single skb_put_zero(), which clears both. The AUTO_MGR sub-TLV carries no payload, so the zeroed length field is already the value it should have. Fixes: f7458934b079 ("net: bridge: mrp: Update the Test frames for MRA") Suggested-by: Nikolay Aleksandrov Cc: stable@vger.kernel.org Signed-off-by: Baul Lee Acked-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20260729131941.10254-1-baul.lee@xbow.com Signed-off-by: Jakub Kicinski --- net/bridge/br_mrp.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 179d2470b724..ef16d0703924 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -224,11 +224,9 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, sub_opt = skb_put(skb, sizeof(*sub_opt)); memset(sub_opt, 0x0, sizeof(*sub_opt)); - sub_tlv = skb_put(skb, sizeof(*sub_tlv)); - sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; - /* 32 bit alligment shall be ensured therefore add 2 bytes */ - skb_put(skb, MRP_OPT_PADDING); + sub_tlv = skb_put_zero(skb, sizeof(*sub_tlv) + MRP_OPT_PADDING); + sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; } br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); From 653d7ddf6cba867777a3d14c4f83ace008c5ad13 Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Tue, 28 Jul 2026 01:23:29 +0800 Subject: [PATCH 032/116] inet: frags: publish queues before arming timer inet_frag_create() arms the fragment queue timer before inserting the queue into the fqdir rhashtable. If the namespace fragment timeout is zero or negative, the timer can run before the queue is published. The timer callback then marks the queue complete, tries to remove a node that is not in the hash table yet, and drops the anticipated hash reference. Creation can subsequently publish the completed queue without restoring that reference, leaving a stale hash node after the caller drops the remaining reference. Publish the queue first and arm the timer while holding the queue lock. This makes timer expiry wait until the queue is visible in the hash table, so inet_frag_kill() can remove the node and balance the hash reference. Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zhiling Zou Signed-off-by: Ren Wei Link: https://patch.msgid.link/bf66785e7c0c139d7a1900e2f01faeeab344b960.1784948849.git.zhilinz@nebusec.ai Signed-off-by: Jakub Kicinski --- net/ipv4/inet_fragment.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 848c0f0c2ed9..fc0cb993959f 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -393,8 +393,8 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, *prev = ERR_PTR(-ENOMEM); return NULL; } - mod_timer(&q->timer, jiffies + fqdir->timeout); + spin_lock_bh(&q->lock); *prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key, &q->node, f->rhash_params); if (*prev) { @@ -402,13 +402,13 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, * we need to cancel what inet_frag_alloc() * anticipated. */ - int refs = 1; - q->flags |= INET_FRAG_COMPLETE; - inet_frag_kill(q, &refs); - inet_frag_putn(q, refs); + spin_unlock_bh(&q->lock); + inet_frag_putn(q, 2); return NULL; } + mod_timer(&q->timer, jiffies + fqdir->timeout); + spin_unlock_bh(&q->lock); return q; } From 47d7f7051253bdc02b1d245d87e38f16d31a74df Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Wed, 29 Jul 2026 05:44:11 -0400 Subject: [PATCH 033/116] net/sched: cls_route: fix fastmap use-after-free on filter The route4 classifier maintains a 16-slot fastmap cache that stores raw struct route4_filter pointers indexed by (id, iif). The reader (route4_classify) populates this cache via route4_set_fastmap() for every classified packet that hits a filter. The writer (route4_delete, route4_change) clears the cache via route4_reset_fastmap() before RCU-deferred kfree of the filter. This creates a UAF race: 1. Reader walks the RCU-protected bucket chain, finds filter f 2. Writer unlinks f, calls route4_reset_fastmap(), then tcf_queue_work() 3. Reader calls route4_set_fastmap() and writes f into the cache *after* the writer's reset, caching a pointer about to be freed 4. After the RCU grace period, kfree(f) executes 5. Next classified packet on the same (id, iif) tuple hits the stale fastmap entry and reads f->res from freed memory Reproduced with an mdelay(100) accelerator in route4_set_fastmap() and a concurrent add/delete stress test (provided by both zdi and Santosh). Both triggered KASAN slab-use-after-free reports in the route4 fastmap paths. Fix: Introduce a per-filter boolean dying flag to suppress stale fastmap republishing by in-flight readers. Fixes: 1109c00547fc ("net: sched: RCU cls_route") Reported-by: zdi-disclosures@trendmicro.com Reported-by: Santosh Kalluri Suggested-by: Paolo Abeni Tested-by: Victor Nogueira Tested-by: Santosh Kalluri Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260729094411.46257-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski --- net/sched/cls_route.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index bd6f945bd388..eded7aacd3f7 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -52,6 +52,7 @@ struct route4_filter { struct tcf_result res; struct tcf_exts exts; u32 handle; + bool dying; struct route4_bucket *bkt; struct tcf_proto *tp; struct rcu_work rwork; @@ -66,9 +67,11 @@ static inline int route4_fastmap_hash(u32 id, int iif) static DEFINE_SPINLOCK(fastmap_lock); static void -route4_reset_fastmap(struct route4_head *head) +route4_reset_fastmap(struct route4_head *head, struct route4_filter *f) { spin_lock_bh(&fastmap_lock); + if (f) + f->dying = true; memset(head->fastmap, 0, sizeof(head->fastmap)); spin_unlock_bh(&fastmap_lock); } @@ -81,9 +84,11 @@ route4_set_fastmap(struct route4_head *head, u32 id, int iif, /* fastmap updates must look atomic to aling id, iff, filter */ spin_lock_bh(&fastmap_lock); - head->fastmap[h].id = id; - head->fastmap[h].iif = iif; - head->fastmap[h].filter = f; + if (f == ROUTE4_FAILURE || !f->dying) { + head->fastmap[h].id = id; + head->fastmap[h].iif = iif; + head->fastmap[h].filter = f; + } spin_unlock_bh(&fastmap_lock); } @@ -297,6 +302,13 @@ static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, next = rtnl_dereference(f->next); RCU_INIT_POINTER(b->ht[h2], next); tcf_unbind_filter(tp, &f->res); + /* Mark the filter dying under fastmap_lock so + * any in-flight reader that still holds it + * will skip the republish in route4_set_fastmap(). + */ + spin_lock_bh(&fastmap_lock); + f->dying = true; + spin_unlock_bh(&fastmap_lock); if (tcf_exts_get_net(&f->exts)) route4_queue_work(f); else @@ -307,6 +319,11 @@ static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, kfree_rcu(b, rcu); } } + + /* All filters are unlinked and marked dying, so no in-flight + * reader can republish a stale entry after this reset. + */ + route4_reset_fastmap(head, NULL); kfree_rcu(head, rcu); } @@ -334,11 +351,11 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, /* unlink it */ RCU_INIT_POINTER(*fp, rtnl_dereference(f->next)); - /* Remove any fastmap lookups that might ref filter - * notice we unlink'd the filter so we can't get it - * back in the fastmap. + /* Clear any fastmap entries that may ref this filter and + * mark it dying so in-flight readers can't republish it + * after the reset. */ - route4_reset_fastmap(head); + route4_reset_fastmap(head, f); /* Delete it */ tcf_unbind_filter(tp, &f->res); @@ -558,7 +575,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, } } - route4_reset_fastmap(head); + route4_reset_fastmap(head, fold); *arg = f; if (fold) { tcf_unbind_filter(tp, &fold->res); From f307a7dc32097c11413178fca437a10d20890bc2 Mon Sep 17 00:00:00 2001 From: Jiawen Liu <1298662399@qq.com> Date: Tue, 28 Jul 2026 12:17:10 +0400 Subject: [PATCH 034/116] net: hisilicon: hix5hd2_gmac: remove redundant NAPI delete hix5hd2_dev_remove() calls netif_napi_del() before unregister_netdev(). This is not needed because free_netdev() deletes all NAPI instances attached to the net_device. Remove the redundant call and let the networking core tear down the NAPI instance during unregister_netdev(). The probe error path still keeps its explicit netif_napi_del(), because the device has not been registered there. Fixes: 57c5bc9ad7d7 ("net: hisilicon: add hix5hd2 mac driver") Signed-off-by: Jiawen Liu <1298662399@qq.com> Link: https://patch.msgid.link/tencent_5FFD37A252B4FEA6A80AD25B17C8E904F005@qq.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hix5hd2_gmac.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index e3e7f2270560..02282dc86faf 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -1282,7 +1282,6 @@ static void hix5hd2_dev_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct hix5hd2_priv *priv = netdev_priv(ndev); - netif_napi_del(&priv->napi); unregister_netdev(ndev); mdiobus_unregister(priv->bus); mdiobus_free(priv->bus); From 1c4dac9bf1d2ac31da63b794bdec697777cbd0fd Mon Sep 17 00:00:00 2001 From: Or Har-Toov Date: Wed, 29 Jul 2026 11:06:00 +0300 Subject: [PATCH 035/116] devlink: fix net namespace reference leak in reload devlink_nl_reload_doit() calls devlink_netns_get(), which returns a net with a held reference. When the requested namespace differs from the current one and the reload action is not DRIVER_REINIT, the function returns -EOPNOTSUPP without releasing the reference. Add the missing put_net() on this error path. Fixes: 2edd92570441 ("devlink: don't allow to change net namespace for FW_ACTIVATE reload action") Signed-off-by: Or Har-Toov Reviewed-by: Jiri Pirko Signed-off-by: Tariq Toukan Reviewed-by: Antoine Tenart Link: https://patch.msgid.link/20260729080600.2427721-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- net/devlink/dev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 57b2b8f03543..fd5633fa88ec 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -578,6 +578,7 @@ int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info) action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT) { NL_SET_ERR_MSG_MOD(info->extack, "Changing namespace is only supported for reinit action"); + put_net(dest_net); return -EOPNOTSUPP; } } From 43e970d961ad3cc0c23e89db255c7fa4a353eff9 Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Wed, 29 Jul 2026 10:16:22 +0300 Subject: [PATCH 036/116] net/mlx5: SF, Handle function changed event When host is powered off, firmware does not send vhca_state event for every probed host SF on the DPU because it may have deployed thousands of SFs to the host. Instead it sends a function changed event. Currently, only VFs handle this event. This commit extends support to SFs. When DPU user deactivates[1] SFs, mlx5 expects vhca_state event and leaves the SF in dangling state[2]. When DPU user deletes[3] SFs, mlx5 also expects vhca_state event and destroys the SF resources[4]. Fix it by changing SF to the right state and freeing SF resources when the function changed event is received. When this event is received, driver checks all SF states. - If state is in_use, change it to active. - If state is teardown_request, change it to allocated. And SF hardware table entry is freed if it is pending for delete. [1] # devlink port function set en3f0c1pf0sf0 state inactive [2] # devlink port function set en3f0c1pf0sf0 state active Error: mlx5_core: SF is inactivated but it is still attached. kernel answers: Device or resource busy [3] # devlink port show pci/0000:03:00.0/229376: type eth netdev en3f0c1pf0sf0 \ flavour pcisf controller 1 pfnum 0 sfnum 0 splittable false function: hw_addr 00:00:00:00:00:00 state active opstate attached \ roce enable trust off max_uc_macs 4096 max_io_eqs 8 # devlink port del en3f0c1pf0sf0 [4] # devlink port add pci/0000:03:00.0 flavour pcisf pfnum 0 sfnum 0 \ controller 1 Error: mlx5_core: SF already exist. Choose different sfnum. kernel answers: File exists Fixes: 6a3273217469 ("net/mlx5: SF, Port function state change support") Signed-off-by: Chris Mi Reviewed-by: Shay Drori Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260729071622.2423270-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../mellanox/mlx5/core/eswitch_offloads.c | 10 +++++-- .../ethernet/mellanox/mlx5/core/sf/devlink.c | 29 +++++++++++++++++++ .../mlx5/core/sf/diag/sf_tracepoint.h | 8 +++++ .../ethernet/mellanox/mlx5/core/sf/hw_table.c | 22 ++++++++++++++ .../net/ethernet/mellanox/mlx5/core/sf/sf.h | 12 ++++++++ 5 files changed, 78 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 907ee83a722d..247e5d85ec36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3986,7 +3986,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) mutex_destroy(&esw->fdb_table.offloads.vports.lock); } -static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw) +static void esw_changed_event_handler(struct mlx5_eswitch *esw) { struct mlx5_esw_pf_info host_pf_info; u16 new_num_vfs; @@ -3999,6 +3999,11 @@ static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw) host_pf_info = mlx5_esw_get_host_pf_info(esw->dev, out); new_num_vfs = host_pf_info.num_of_vfs; + if (host_pf_info.pf_disabled) { + mlx5_sf_table_esw_changed_event_handler(esw->dev); + mlx5_sf_hw_table_esw_changed_event_handler(esw->dev); + } + if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_info.pf_disabled) goto free; @@ -4091,8 +4096,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, esw_funcs = mlx5_nb_cof(nb, struct mlx5_esw_functions, nb); esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs); - ret = mlx5_esw_add_work(esw, esw_vfs_changed_event_handler, - GFP_ATOMIC); + ret = mlx5_esw_add_work(esw, esw_changed_event_handler, GFP_ATOMIC); if (ret) return NOTIFY_DONE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index b6cecbcc392d..4564d460416b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -561,3 +561,32 @@ bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev) return xa_empty(&table->function_ids); } + +void mlx5_sf_table_esw_changed_event_handler(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_table *table = dev->priv.sf_table; + unsigned long index; + struct mlx5_sf *sf; + + trace_mlx5_sf_host_pf_disabled(dev); + + if (!table) + return; + + mutex_lock(&table->sf_state_lock); + xa_for_each(&table->function_ids, index, sf) { + if (!sf->controller) + continue; + + if (sf->hw_state == MLX5_VHCA_STATE_IN_USE) + sf->hw_state = MLX5_VHCA_STATE_ACTIVE; + else if (sf->hw_state == MLX5_VHCA_STATE_TEARDOWN_REQUEST) + sf->hw_state = MLX5_VHCA_STATE_ALLOCATED; + else + continue; + trace_mlx5_sf_update_state(table->dev, sf->port_index, + sf->controller, sf->hw_fn_id, + sf->hw_state); + } + mutex_unlock(&table->sf_state_lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h index 302ce00da5a9..9dc88a7e30ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h @@ -11,6 +11,14 @@ #include #include "sf/vhca_event.h" +TRACE_EVENT(mlx5_sf_host_pf_disabled, + TP_PROTO(const struct mlx5_core_dev *dev), + TP_ARGS(dev), + TP_STRUCT__entry(__string(devname, dev_name(dev->device))), + TP_fast_assign(__assign_str(devname);), + TP_printk("(%s)\n", __get_str(devname)) +); + TRACE_EVENT(mlx5_sf_add, TP_PROTO(const struct mlx5_core_dev *dev, unsigned int port_index, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c index 0bc9146a3598..95a8b1e64ba4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -459,3 +459,25 @@ bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev) { return !!dev->priv.sf_hw_table; } + +void mlx5_sf_hw_table_esw_changed_event_handler(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_hw_table *table; + struct mlx5_sf_hwc_table *hwc; + int i; + + table = dev->priv.sf_hw_table; + if (!table) + return; + + mutex_lock(&table->table_lock); + hwc = &table->hwc[MLX5_SF_HWC_EXT_HOST]; + for (i = 0; i < hwc->max_fn; i++) { + struct mlx5_sf_hw *sf_hw; + + sf_hw = &hwc->sfs[i]; + if (sf_hw->allocated && sf_hw->pending_delete) + mlx5_sf_hw_table_hwc_sf_free(dev, hwc, i); + } + mutex_unlock(&table->table_lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h index d8a934a0e968..ed784682b9b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h @@ -15,12 +15,14 @@ void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev); int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev); void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev); void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev); +void mlx5_sf_hw_table_esw_changed_event_handler(struct mlx5_core_dev *dev); int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev); int mlx5_sf_table_init(struct mlx5_core_dev *dev); void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev); void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev); bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev); +void mlx5_sf_table_esw_changed_event_handler(struct mlx5_core_dev *dev); int mlx5_devlink_sf_port_new(struct devlink *devlink, const struct devlink_port_new_attrs *add_attr, @@ -60,6 +62,11 @@ static inline void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev) { } +static inline void +mlx5_sf_hw_table_esw_changed_event_handler(struct mlx5_core_dev *dev) +{ +} + static inline int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev) { return 0; @@ -83,6 +90,11 @@ static inline bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev) return true; } +static inline void +mlx5_sf_table_esw_changed_event_handler(struct mlx5_core_dev *dev) +{ +} + #endif #endif From af39eb111ce6b5eba9c08513b62c4868eb7e7fd5 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Wed, 29 Jul 2026 11:04:02 +0300 Subject: [PATCH 037/116] net/mlx5: fw_tracer, return NULL on create error Tracer creation can fail by returning either NULL or ERR_PTR. The return value is stored without a check on the device, and users treat ERR_PTR and NULL the same way. This also causes a crash in the core dump logic, which is missing the ERR_PTR check and ends up dereferencing it, as shown in the trace below. Switch tracer creation to return NULL on failure only, so callers only need a single NULL check. Internal error: Oops: 0000000096000006 [#1] SMP Modules linked in: mlx5_ib ib_uverbs ib_core ipv6 mlx5_core CPU: 1 UID: 0 PID: 12 Comm: kworker/u16:0 Not tainted 6.19.7 #1 PREEMPT(none) Workqueue: mlx5_health0001:01:00.0 mlx5_fw_reporter_err_work [mlx5_core] pstate: a3400009 (NzCv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : mlx5_fw_tracer_trigger_core_dump_general+0x58/0xe0 [mlx5_core] lr : mlx5_fw_tracer_trigger_core_dump_general+0x40/0xe0 [mlx5_core] sp : ffff800081cf3c40 x29: ffff800081cf3c90 x28: 0000000000000000 x27: 0000000000000000 x26: ffff000080018828 x25: 0000000000000000 x24: ffff000080304a05 x23: ffff800081cf3d80 x22: ffff0000847e01a0 x21: 0000000000000000 x20: ffff0000847e01a0 x19: ffffffffffffffa1 x18: ffff80008310bbf0 x17: ffff800080119650 x16: ffff80008010df54 x15: ffff80008010d4ac x14: ffff800079c202e4 x13: ffff80008002fe60 x12: ffff800080119650 x11: ffff80008010df54 x10: ffff80008010d4ac x9 : ffff800079c203d8 x8 : ffff800081cf3c88 x7 : 0000000000000000 x6 : 0000000000000000 x5 : 0000000000000000 x4 : 0000000000000008 x3 : 0000000000000030 x2 : 0000000000000008 x1 : 0000000000000000 x0 : 00000000c5c4000e Call trace: mlx5_fw_tracer_trigger_core_dump_general+0x58/0xe0 [mlx5_core] (P) mlx5_fw_reporter_dump+0x30/0x2e0 [mlx5_core] devlink_health_do_dump+0x9c/0x160 devlink_health_report+0x1c0/0x288 mlx5_fw_reporter_err_work+0xac/0xc0 [mlx5_core] process_one_work+0x15c/0x3d8 worker_thread+0x18c/0x320 kthread+0x148/0x228 ret_from_fork+0x10/0x20 Code: b9400000 5ac00800 7a401800 540003ca (3940a260) ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Oops: Fatal exception SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x000000,00078031,75fce5a1,35fffe67 Memory Limit: none ---[ end Kernel panic - not syncing: Oops: Fatal exception ]--- Fixes: fd1483fe1f9f ("net/mlx5: Add support for FW reporter dump") Signed-off-by: Michael Guralnik Reviewed-by: Shay Drori Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260729080402.2427184-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index adcc73e2a5b3..1493d8106c1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1025,13 +1025,11 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) tracer = kvzalloc_obj(*tracer); if (!tracer) - return ERR_PTR(-ENOMEM); + return NULL; tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer"); - if (!tracer->work_queue) { - err = -ENOMEM; + if (!tracer->work_queue) goto free_tracer; - } tracer->dev = dev; @@ -1073,7 +1071,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) destroy_workqueue(tracer->work_queue); free_tracer: kvfree(tracer); - return ERR_PTR(err); + return NULL; } static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data); @@ -1084,7 +1082,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) struct mlx5_core_dev *dev; int err; - if (IS_ERR_OR_NULL(tracer)) + if (!tracer) return 0; if (!tracer->str_db.loaded) @@ -1134,7 +1132,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) /* Stop tracer + Cleanup HW resources */ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) { - if (IS_ERR_OR_NULL(tracer)) + if (!tracer) return; mutex_lock(&tracer->state_lock); @@ -1163,7 +1161,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) /* Free software resources (Buffers, etc ..) */ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) { - if (IS_ERR_OR_NULL(tracer)) + if (!tracer) return; mlx5_core_dbg(tracer->dev, "FWTracer: Destroy\n"); @@ -1215,7 +1213,7 @@ int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer) struct mlx5_core_dev *dev; int err; - if (IS_ERR_OR_NULL(tracer)) + if (!tracer) return 0; dev = tracer->dev; From 0e125ecfe20c077625cf0be8d750d5c3abc0dce9 Mon Sep 17 00:00:00 2001 From: Nathan Gao Date: Fri, 24 Jul 2026 20:08:06 -0700 Subject: [PATCH 038/116] tcp: do not change rcv_ssthresh in tcp_measure_rcv_mss() Commit f5da7c45188e ("tcp: adjust rcvq_space after updating scaling ratio") replaced the direct window_clamp update in tcp_measure_rcv_mss() with a call to tcp_set_window_clamp(), a helper that implements the TCP_WINDOW_CLAMP setsockopt. As a side effect, the helper also shrinks rcv_ssthresh via __tcp_adjust_rcv_ssthresh(). As a result, each scaling_ratio decrease detected by tcp_measure_rcv_mss() also cuts rcv_ssthresh. Elsewhere in TCP, rcv_ssthresh is usually cut under memory pressure and grows via tcp_grow_window(). Flows whose segment sizes vary keep scaling_ratio oscillating, which leads to an unstable rcv_ssthresh: a dip of rcv_ssthresh only recovers via tcp_grow_window(), keeping the advertised window at a relatively low level even after the ratio itself has recovered, and can even stall the sender. Observed on a customer's proxy gateway after upgrading from kernel 6.1 to 6.12: in the worst case, rcv_ssthresh was cut in half by a scaling_ratio dip. P99 latency jumped from <10ms on 6.1 to ~100ms on 6.12, and almost returned to the 6.1 level with this patch applied. Restore the plain WRITE_ONCE() update of window_clamp, as introduced in commit a2cbb1603943 ("tcp: Update window clamping condition"), and keep the rcvq_space.space adjustment. Now rcv_ssthresh is decoupled from scaling_ratio changes in tcp_measure_rcv_mss(). Fixes: f5da7c45188e ("tcp: adjust rcvq_space after updating scaling ratio") Signed-off-by: Nathan Gao Link: https://patch.msgid.link/20260725030806.28135-1-zcgao@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index daff93d51342..5b6378b94701 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -252,7 +252,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); val = tcp_win_from_space(sk, sk->sk_rcvbuf); - tcp_set_window_clamp(sk, val); + WRITE_ONCE(tp->window_clamp, val); if (tp->window_clamp < tp->rcvq_space.space) tp->rcvq_space.space = tp->window_clamp; From 9f2cf069a9a72a2d6b97ca8b4c70e714aac99749 Mon Sep 17 00:00:00 2001 From: Baul Lee Date: Thu, 30 Jul 2026 01:00:28 +0900 Subject: [PATCH 039/116] sctp: keep chunk->transport in step with the list it is queued on __sctp_outq_flush_rtx() moves a gap-acked chunk onto another transport's transmitted list without updating chunk->transport: if (chunk->tsn_gap_acked) { list_move_tail(&chunk->transmitted_list, &transport->transmitted); continue; } The chunk then sits on a live transport's list while chunk->transport still names a different one. If that transport is removed - sctp_assoc_rm_peer() from an ASCONF Delete-IP - sctp_transport_free() RCU-frees it and the chunk is left with a dangling pointer. sctp_assoc_rm_peer() scrubs peer->transmitted and asoc->outqueue.out_chunk_list, but the chunk is on neither. The pointer is not followed while tsn_gap_acked is set. A SACK that reneges on the TSN clears the flag, and the next SACK reaches tchunk->transport->flight_size -= sctp_data_size(tchunk); inside the freed transport. KASAN reports a slab-use-after-free read in sctp_check_transmitted(), freed from sctp_assoc_rm_peer(). Both the removal and the SACKs come from the association peer. Set chunk->transport at the move. The ordinary resend path needs nothing: it reaches its list_move_tail() only after sctp_packet_append_chunk() returned SCTP_XMIT_OK, and __sctp_packet_append_chunk() has rebound the chunk by then. Discovered by XBOW, triaged by Baul Lee Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Baul Lee Acked-by: Xin Long Link: https://patch.msgid.link/20260729160028.54546-1-baul.lee@xbow.com Signed-off-by: Jakub Kicinski --- net/sctp/outqueue.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index f6b8c13dafa4..e92fb9da4647 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -650,6 +650,7 @@ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, if (chunk->tsn_gap_acked) { list_move_tail(&chunk->transmitted_list, &transport->transmitted); + chunk->transport = transport; continue; } From d1ad8fb2ac6a1afb71dc22d9ae8efb4dda96c824 Mon Sep 17 00:00:00 2001 From: Yuejie Shi Date: Thu, 30 Jul 2026 11:52:32 +0800 Subject: [PATCH 040/116] ipv6: fix Route Information option length validation rt6_route_rcv() validates the Route Information option (RFC 4191) length against the prefix length, but both checks are off by one. rinfo->length is the ND option length in units of 8 octets and it *includes* the 8-byte option header, so an option carrying N bytes of prefix has length == 1 + N/8. RFC 4191 section 2.3 requires length 3 when Prefix Length is greater than 64, and 2 or 3 when it is greater than 0. The code accepts length >= 2 and length >= 1 respectively. ipv6_addr_prefix() then copies prefix_len/8 bytes out of rinfo->prefix, so a Router Advertisement with (prefix_len=128, length=2) or (prefix_len=64, length=1) makes the kernel read up to 8 bytes past the end of the option. Those bytes end up in the prefix of the route that gets installed, so they are visible to userspace: # RA with a Route Information option (prefix_len=128, length=2) # followed by a source link-layer address option, 01 01 de ad be ef ca fe $ ip -6 route show 2001:db8:dead:beef:101:dead:beef:cafe via fe80::1234 dev veth0 proto ra ^^^^^^^^^^^^^^^^^^ the next option, read out of bounds When the Route Information option is the last one in the packet, those eight bytes come from the skb tail room instead. Reject the option lengths RFC 4191 does not allow. Fixes: 70ceb4f53929 ("[IPV6]: ROUTE: Add experimental support for Route Information Option in RA (RFC4191).") Cc: stable@vger.kernel.org Signed-off-by: Yuejie Shi Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260730035310.74584-1-syjcnss@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv6/route.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fc42d67e5822..5968ce5ad150 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -988,13 +988,13 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, } else if (rinfo->prefix_len > 128) { return -EINVAL; } else if (rinfo->prefix_len > 64) { - if (rinfo->length < 2) { + /* RFC 4191: Length MUST be 3 when Prefix Length > 64 */ + if (rinfo->length < 3) return -EINVAL; - } } else if (rinfo->prefix_len > 0) { - if (rinfo->length < 1) { + /* RFC 4191: Length MUST be 2 or 3 when Prefix Length > 0 */ + if (rinfo->length < 2) return -EINVAL; - } } pref = rinfo->route_pref; From d1000fd7995e51deec872d154e0a40d82f7a539f Mon Sep 17 00:00:00 2001 From: Will Chen Date: Wed, 29 Jul 2026 15:01:31 -0700 Subject: [PATCH 041/116] bnxt: fix memory leak in bnxt_queue_mem_alloc error cases There is a small memory leak in bnxt_queue_mem_alloc: when bnxt_alloc_rx_agg_bmap() succeeds but bnxt_alloc_one_tpa_info() later fails, the rx_agg_bmap allocated by bnxt_alloc_rx_agg_bmap() is not freed in the fallthrough cleanup cases. Free the rx_agg_bmap in the err_free_rx_agg_ring case and initialize clone->rx_agg_bmap = NULL earlier in the function to allow for safe fallthrough. Fixes: bd649c5cc958 ("bnxt_en: handle tpa_info in queue API implementation") Signed-off-by: Will Chen Reviewed-by: Joe Damato Reviewed-by: Michael Chan Link: https://patch.msgid.link/20260729220132.1256924-1-will.chen.tty@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7513618793da..004ef99f4530 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -16217,6 +16217,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, clone->rx_next_cons = 0; clone->need_head_pool = false; clone->rx_page_size = qcfg->rx_page_size; + clone->rx_agg_bmap = NULL; rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid); if (rc) @@ -16269,6 +16270,8 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, bnxt_free_one_tpa_info(bp, clone); err_free_rx_agg_ring: bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem); + kfree(clone->rx_agg_bmap); + clone->rx_agg_bmap = NULL; err_free_rx_ring: bnxt_free_ring(bp, &clone->rx_ring_struct.ring_mem); err_rxq_info_unreg: From ebac8f6b1ef0e9278afe204b8692a7479988dace Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Wed, 29 Jul 2026 12:16:54 -0700 Subject: [PATCH 042/116] vsock/virtio: read virtqueues under worker locks Commit bd50c5dc182b ("vsock/virtio: add support for device suspend/resume") made the *_run flags transition from false to true when restore installs replacement virtqueues. The RX, TX and event workers read their virtqueue before locking and checking the corresponding flag, so a worker delayed across freeze and restore can observe the replacement queue's running state while retaining a pointer to the deleted queue. Read each virtqueue under its mutex after checking the run flag, keeping the pointer and state in the same queue generation. Fixes: bd50c5dc182b ("vsock/virtio: add support for device suspend/resume") Cc: stable@vger.kernel.org Reported-by: Xiang Mei Link: https://lore.kernel.org/r/20260727035804.1860862-1-bestswngs@gmail.com Signed-off-by: Weiming Shi Reviewed-by: Bobby Eshleman Link: https://patch.msgid.link/e79f68ad9284c983364fc3ac46904b6d9ef50231.1785352330.git.bestswngs@gmail.com Signed-off-by: Jakub Kicinski --- net/vmw_vsock/virtio_transport.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 57f2d6ec3ffc..a8e1dd95ba8c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -346,12 +346,13 @@ static void virtio_transport_tx_work(struct work_struct *work) struct virtqueue *vq; bool added = false; - vq = vsock->vqs[VSOCK_VQ_TX]; mutex_lock(&vsock->tx_lock); if (!vsock->tx_run) goto out; + vq = vsock->vqs[VSOCK_VQ_TX]; + do { struct sk_buff *skb; unsigned int len; @@ -451,13 +452,13 @@ static void virtio_transport_event_work(struct work_struct *work) container_of(work, struct virtio_vsock, event_work); struct virtqueue *vq; - vq = vsock->vqs[VSOCK_VQ_EVENT]; - mutex_lock(&vsock->event_lock); if (!vsock->event_run) goto out; + vq = vsock->vqs[VSOCK_VQ_EVENT]; + do { struct virtio_vsock_event *event; unsigned int len; @@ -634,13 +635,13 @@ static void virtio_transport_rx_work(struct work_struct *work) container_of(work, struct virtio_vsock, rx_work); struct virtqueue *vq; - vq = vsock->vqs[VSOCK_VQ_RX]; - mutex_lock(&vsock->rx_lock); if (!vsock->rx_run) goto out; + vq = vsock->vqs[VSOCK_VQ_RX]; + do { virtqueue_disable_cb(vq); for (;;) { From a31e0ad444698d8aa7534a0f89fda543730f97a5 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Wed, 29 Jul 2026 12:16:55 -0700 Subject: [PATCH 043/116] vsock/virtio: avoid refilling the RX queue after teardown Commit b917507e5ad9 ("vsock/virtio: stop workers during the .remove()") made the RX worker jump to its common exit when rx_run is clear. That exit still refills the RX queue when the buffer count is low, so work queued across virtio_vsock_vqs_del() can add buffers after the virtqueues have been deleted. BUG: KASAN: slab-use-after-free in virtqueue_add_sgs Read of size 4 by task kworker/0:1 Workqueue: virtio_vsock virtio_transport_rx_work Call Trace: virtqueue_add_sgs (drivers/virtio/virtio_ring.c:2796) virtio_vsock_rx_fill (net/vmw_vsock/virtio_transport.c:332) virtio_transport_rx_work (net/vmw_vsock/virtio_transport.c:701) process_one_work (kernel/workqueue.c:3314) worker_thread (kernel/workqueue.c:3478) kthread (kernel/kthread.c:436) ret_from_fork (arch/x86/kernel/process.c:158) ret_from_fork_asm (arch/x86/entry/entry_64.S:245) ... Freed by task 141: kfree (mm/slub.c:6566) vp_del_vq (drivers/virtio/virtio_pci_common.c:259) vp_del_vqs (drivers/virtio/virtio_pci_common.c:285) virtio_vsock_freeze (net/vmw_vsock/virtio_transport.c:912) virtio_device_freeze (drivers/virtio/virtio.c:658) virtio_pci_freeze (drivers/virtio/virtio_pci_common.c:601) pci_pm_freeze (drivers/pci/pci-driver.c:1098) device_suspend (drivers/base/power/main.c:1968) Kernel panic - not syncing: KASAN: panic_on_warn set ... Jump to a no-refill exit when rx_run is clear, leaving the normal exit to replenish a running queue. Fixes: b917507e5ad9 ("vsock/virtio: stop workers during the .remove()") Cc: stable@vger.kernel.org Reported-by: Xiang Mei Link: https://lore.kernel.org/r/20260727035804.1860862-1-bestswngs@gmail.com Suggested-by: Stefano Garzarella Signed-off-by: Weiming Shi Reviewed-by: Bobby Eshleman Link: https://patch.msgid.link/f9c8c1d64cad9d262f305d02ffe164c2f900fadf.1785352330.git.bestswngs@gmail.com Signed-off-by: Jakub Kicinski --- net/vmw_vsock/virtio_transport.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index a8e1dd95ba8c..96c9fe8d357c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -638,7 +638,7 @@ static void virtio_transport_rx_work(struct work_struct *work) mutex_lock(&vsock->rx_lock); if (!vsock->rx_run) - goto out; + goto out_nofill; vq = vsock->vqs[VSOCK_VQ_RX]; @@ -692,6 +692,7 @@ static void virtio_transport_rx_work(struct work_struct *work) out: if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) virtio_vsock_rx_fill(vsock); +out_nofill: mutex_unlock(&vsock->rx_lock); } From 1bb30b181d9f0484e141f8411e15ed906d5c6780 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Jul 2026 09:19:54 -0700 Subject: [PATCH 044/116] xsk: require at least 16 bytes of TX metadata AF_XDP accepts a TX metadata length as small as eight bytes, but every supported request needs the flags plus at least one eight-byte request field. Such short metadata also lets the kernel read beyond the registered area. Require 16 bytes rather than sizeof(struct xsk_tx_metadata) to preserve compatibility with applications that do not use launch-time metadata. Fixes: 341ac980eab9 ("xsk: Support tx_metadata_len") Reported-by: AutonomousCodeSecurity@microsoft.com Reported-by: Cen Zhang (Microsoft) Link: https://lore.kernel.org/netdev/20260720155210.34229-1-blbllhy@gmail.com/ Signed-off-by: Stanislav Fomichev Link: https://patch.msgid.link/20260727161959.885642-2-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- net/xdp/xdp_umem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 58da2f4f4397..cd8643360eb3 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -210,6 +210,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (mr->flags & XDP_UMEM_TX_METADATA_LEN) { if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) return -EINVAL; + if (mr->tx_metadata_len < 16) + return -EINVAL; umem->tx_metadata_len = mr->tx_metadata_len; } From 19366db6dfccac9b0867a151678cd7b89fb8fd99 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Jul 2026 09:19:55 -0700 Subject: [PATCH 045/116] xsk: pass TX metadata pointer by reference Completion handling needs to know whether a timestamp was requested when the metadata was processed. Let xsk_tx_metadata_request() update the caller's metadata pointer so that decision can be carried forward without rereading user-controlled flags. This only changes the interface; behavior remains unchanged. Fixes: ca4419f15abd ("xsk: Add launch time hardware offload support to XDP Tx metadata") Cc: Cen Zhang (Microsoft) Signed-off-by: Stanislav Fomichev Link: https://patch.msgid.link/20260727161959.885642-3-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 14 +++++++++----- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h | 4 ++-- .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- include/net/libeth/xsk.h | 2 +- include/net/xdp_sock.h | 8 +++++--- 8 files changed, 21 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index b3883a5a7d7a..beaea1479485 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3082,7 +3082,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) meta_req.tx_buffer = bi; meta_req.meta = meta; meta_req.used_desc = 0; - xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops, + xsk_tx_metadata_request(&meta, &igc_xsk_tx_metadata_ops, &meta_req); /* xsk_tx_metadata_request() may have updated next_to_use */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 6867a5aed42c..822859c360e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -483,7 +483,7 @@ typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *); typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *, struct mlx5e_xmit_data *, int, - struct xsk_tx_metadata *); + struct xsk_tx_metadata **); struct mlx5e_xdpsq { /* data path */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index d8c7cb8837d7..dac5e9d4c8bd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -452,11 +452,11 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result, struct xsk_tx_metadata *meta); + int check_result, struct xsk_tx_metadata **meta); INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result, struct xsk_tx_metadata *meta) + int check_result, struct xsk_tx_metadata **meta) { struct mlx5e_tx_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; @@ -504,7 +504,10 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx * and it's safe to complete it at any time. */ mlx5e_xdp_mpwqe_session_start(sq); - xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, &session->wqe->eth); + if (meta) + xsk_tx_metadata_request(meta, + &mlx5e_xsk_tx_metadata_ops, + &session->wqe->eth); } mlx5e_xdp_mpwqe_add_dseg(sq, p, stats); @@ -535,7 +538,7 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq) INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result, struct xsk_tx_metadata *meta) + int check_result, struct xsk_tx_metadata **meta) { struct mlx5e_xmit_data_frags *xdptxdf = container_of(xdptxd, struct mlx5e_xmit_data_frags, xd); @@ -649,7 +652,8 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, sq->pc += num_wqebbs; - xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg); + if (meta) + xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg); sq->doorbell_cseg = cseg; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 3c54f8962664..5b8f4094d553 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -114,11 +114,11 @@ extern const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops; INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, int check_result, - struct xsk_tx_metadata *meta)); + struct xsk_tx_metadata **meta)); INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, int check_result, - struct xsk_tx_metadata *meta)); + struct xsk_tx_metadata **meta)); INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)); INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 8aeab4b21035..3d19dad8f868 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -105,7 +105,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, mlx5e_xmit_xdp_frame, sq, &xdptxd, - check_result, meta); + check_result, &meta); if (unlikely(!ret)) { if (sq->mpwqe.wqe) mlx5e_xdp_mpwqe_complete(sq); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3801f9d45278..7c3a7c56a81a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2748,7 +2748,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) meta_req.set_ic = &set_ic; meta_req.tbs = tx_q->tbs; meta_req.edesc = &tx_q->dma_entx[entry]; - xsk_tx_metadata_request(meta, &stmmac_xsk_tx_metadata_ops, + xsk_tx_metadata_request(&meta, &stmmac_xsk_tx_metadata_ops, &meta_req); if (set_ic) { tx_q->tx_count_frames = 0; diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h index 82b5d21aae87..e2fa6bf6b1b3 100644 --- a/include/net/libeth/xsk.h +++ b/include/net/libeth/xsk.h @@ -205,7 +205,7 @@ __libeth_xsk_xmit_fill_buf_md(const struct xdp_desc *xdesc, BUILD_BUG_ON(!__builtin_constant_p(tmo == libeth_xsktmo)); tmo = tmo == libeth_xsktmo ? &__libeth_xsktmo : tmo; - xsk_tx_metadata_request(ctx.meta, tmo, &desc); + xsk_tx_metadata_request(&ctx.meta, tmo, &desc); return desc; } diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 8b51876efbed..06c081feff42 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -153,17 +153,19 @@ static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, /** * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission * and call appropriate xsk_tx_metadata_ops operation. - * @meta: pointer to AF_XDP metadata area + * @pmeta: pointer to pointer to AF_XDP metadata area * @ops: pointer to struct xsk_tx_metadata_ops * @priv: pointer to driver-private aread * * This function should be called by the networking device when * it prepares AF_XDP egress packet. */ -static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta, +static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, const struct xsk_tx_metadata_ops *ops, void *priv) { + const struct xsk_tx_metadata *meta = *pmeta; + if (!meta) return; @@ -231,7 +233,7 @@ static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, { } -static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta, +static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, const struct xsk_tx_metadata_ops *ops, void *priv) { From 9f60a67df8d3c862503bee62bada8e7089cba438 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Jul 2026 09:19:56 -0700 Subject: [PATCH 046/116] xsk: clear metadata pointer when no timestamp is requested User space can change metadata flags after request processing. Rereading them during completion can therefore make the kernel write a timestamp that was not requested when the packet was submitted. Clear the metadata pointer during request processing unless timestamp completion is requested. Completion handling can then use the pointer itself instead of rereading the flags. On the mlx5 multi-packet WQE path metadata is evaluated per batch: xsk_tx_metadata_request() runs only for the descriptor that starts a session, just like the checksum offload that is applied once through the shared WQE. Only that descriptor's pointer is reset, so completion handling can record a timestamp for the other descriptors of the session regardless of their own XDP_TXMD_FLAGS_TIMESTAMP bit. The write stays inside the metadata area; the single-WQE, other zero-copy, and generic paths reset the pointer per descriptor and are unaffected. Fixes: ca4419f15abd ("xsk: Add launch time hardware offload support to XDP Tx metadata") Cc: Cen Zhang (Microsoft) Signed-off-by: Stanislav Fomichev Link: https://patch.msgid.link/20260727161959.885642-4-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- include/net/xdp_sock.h | 14 ++++++++++---- net/xdp/xsk.c | 2 ++ 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 06c081feff42..2b2eb9b9d580 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -141,13 +141,16 @@ INDIRECT_CALLABLE_DECLARE(void xsk_destruct_skb(struct sk_buff *)); static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, struct xsk_tx_metadata_compl *compl) { + compl->tx_timestamp = NULL; + if (!meta) return; - if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) - compl->tx_timestamp = &meta->completion.tx_timestamp; - else - compl->tx_timestamp = NULL; + /* we can only arrive here if the completion timestamp has been + * requested via XDP_TXMD_FLAGS_TIMESTAMP, see xsk_tx_metadata_request + */ + + compl->tx_timestamp = &meta->completion.tx_timestamp; } /** @@ -182,6 +185,9 @@ static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) ops->tmo_request_checksum(meta->request.csum_start, meta->request.csum_offset, priv); + + if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)) + *pmeta = NULL; } /** diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index f906d51b6699..fcc6f17f3576 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -998,6 +998,8 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) skb->skb_mstamp_ns = meta->request.launch_time; + if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)) + meta = NULL; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); return 0; From 439ce2dddf3d22129b9113a7881637256a35e936 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Jul 2026 09:19:57 -0700 Subject: [PATCH 047/116] xsk: validate launch-time metadata size Launch-time metadata extends beyond the first 16 bytes of struct xsk_tx_metadata. Reject the request when the registered metadata area does not contain the complete field. Snapshot the validated flags for the generic transmit path and use that snapshot for request and completion processing, avoiding inconsistent decisions if user space changes the flags concurrently. Note that only xsk_skb_metadata is properly using the flags, __xsk_buff_get_metadata ignores them. Next commits address that. Fixes: ca4419f15abd ("xsk: Add launch time hardware offload support to XDP Tx metadata") Cc: Cen Zhang (Microsoft) Signed-off-by: Stanislav Fomichev Link: https://patch.msgid.link/20260727161959.885642-5-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- include/net/xdp_sock_drv.h | 17 +++++++++++++---- net/xdp/xsk.c | 11 ++++++----- 2 files changed, 19 insertions(+), 9 deletions(-) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 46797645a0c2..68a787601357 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -260,21 +260,28 @@ xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) 0) static inline bool -xsk_buff_valid_tx_metadata(const struct xsk_tx_metadata *meta) +xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool, + const struct xsk_tx_metadata *meta, u64 *flags) { - return !(meta->flags & ~XDP_TXMD_FLAGS_VALID); + *flags = READ_ONCE(meta->flags); + if (*flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + if (pool->tx_metadata_len < + offsetofend(struct xsk_tx_metadata, request.launch_time)) + return false; + return !(*flags & ~XDP_TXMD_FLAGS_VALID); } static inline struct xsk_tx_metadata * __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data) { struct xsk_tx_metadata *meta; + u64 flags; if (!pool->tx_metadata_len) return NULL; meta = data - pool->tx_metadata_len; - if (unlikely(!xsk_buff_valid_tx_metadata(meta))) + if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) return NULL; /* no way to signal the error to the user */ return meta; @@ -469,7 +476,9 @@ xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) return (struct xdp_desc_ctx){ }; } -static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) +static inline bool +xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool, + const struct xsk_tx_metadata *meta, u64 *flags) { return false; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index fcc6f17f3576..7855ee09c4b6 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -967,15 +967,16 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, { struct xsk_tx_metadata *meta = NULL; u16 csum_start, csum_offset; + u64 flags; if (unlikely(pool->tx_metadata_len == 0)) return -EINVAL; meta = buffer - pool->tx_metadata_len; - if (unlikely(!xsk_buff_valid_tx_metadata(meta))) + if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) return -EINVAL; - if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) { + if (flags & XDP_TXMD_FLAGS_CHECKSUM) { csum_start = READ_ONCE(meta->request.csum_start); csum_offset = READ_ONCE(meta->request.csum_offset); @@ -996,9 +997,9 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, } } - if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) - skb->skb_mstamp_ns = meta->request.launch_time; - if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)) + if (flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + skb->skb_mstamp_ns = READ_ONCE(meta->request.launch_time); + if (!(flags & XDP_TXMD_FLAGS_TIMESTAMP)) meta = NULL; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); From ddd0d6c5bfe2fef7c7cf31f62265f29b7b9eb9ef Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Jul 2026 09:19:58 -0700 Subject: [PATCH 048/116] xsk: move xsk_tx_metadata_request() to xdp_sock_drv.h xsk_tx_metadata_request() must validate metadata with xsk_buff_valid_tx_metadata(), which is defined in xdp_sock_drv.h. Move the helper there before adding that dependency. All callers already include the destination header, so this has no functional effect. Fixes: ca4419f15abd ("xsk: Add launch time hardware offload support to XDP Tx metadata") Cc: Cen Zhang (Microsoft) Signed-off-by: Stanislav Fomichev Link: https://patch.msgid.link/20260727161959.885642-6-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- include/net/xdp_sock.h | 43 -------------------------------------- include/net/xdp_sock_drv.h | 43 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 43 deletions(-) diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 2b2eb9b9d580..6e70b320b399 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -153,43 +153,6 @@ static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, compl->tx_timestamp = &meta->completion.tx_timestamp; } -/** - * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission - * and call appropriate xsk_tx_metadata_ops operation. - * @pmeta: pointer to pointer to AF_XDP metadata area - * @ops: pointer to struct xsk_tx_metadata_ops - * @priv: pointer to driver-private aread - * - * This function should be called by the networking device when - * it prepares AF_XDP egress packet. - */ -static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, - const struct xsk_tx_metadata_ops *ops, - void *priv) -{ - const struct xsk_tx_metadata *meta = *pmeta; - - if (!meta) - return; - - if (ops->tmo_request_launch_time) - if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) - ops->tmo_request_launch_time(meta->request.launch_time, - priv); - - if (ops->tmo_request_timestamp) - if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) - ops->tmo_request_timestamp(priv); - - if (ops->tmo_request_checksum) - if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) - ops->tmo_request_checksum(meta->request.csum_start, - meta->request.csum_offset, priv); - - if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)) - *pmeta = NULL; -} - /** * xsk_tx_metadata_complete - Evaluate AF_XDP TX metadata at completion * and call appropriate xsk_tx_metadata_ops operation. @@ -239,12 +202,6 @@ static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, { } -static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, - const struct xsk_tx_metadata_ops *ops, - void *priv) -{ -} - static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, const struct xsk_tx_metadata_ops *ops, void *priv) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 68a787601357..f87c4215673e 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -271,6 +271,43 @@ xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool, return !(*flags & ~XDP_TXMD_FLAGS_VALID); } +/** + * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission + * and call appropriate xsk_tx_metadata_ops operation. + * @pmeta: pointer to pointer to AF_XDP metadata area + * @ops: pointer to struct xsk_tx_metadata_ops + * @priv: pointer to driver-private aread + * + * This function should be called by the networking device when + * it prepares AF_XDP egress packet. + */ +static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ + const struct xsk_tx_metadata *meta = *pmeta; + + if (!meta) + return; + + if (ops->tmo_request_launch_time) + if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + ops->tmo_request_launch_time(meta->request.launch_time, + priv); + + if (ops->tmo_request_timestamp) + if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) + ops->tmo_request_timestamp(priv); + + if (ops->tmo_request_checksum) + if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) + ops->tmo_request_checksum(meta->request.csum_start, + meta->request.csum_offset, priv); + + if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)) + *pmeta = NULL; +} + static inline struct xsk_tx_metadata * __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data) { @@ -483,6 +520,12 @@ xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool, return false; } +static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ +} + static inline struct xsk_tx_metadata * __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data) { From 849b1664dbda1cf6c63e0fd4f9dec23782b8c851 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Jul 2026 09:19:59 -0700 Subject: [PATCH 049/116] xsk: validate metadata when processing requests The zero-copy path validates TX metadata while obtaining the descriptor context, then reads it again later when preparing the hardware request. User space can change the metadata between those operations and bypass the original validation. Validate the metadata in xsk_tx_metadata_request() and use the resulting flags snapshot for every feature check. Read request fields once so all zero-copy drivers process only values observed after successful validation. Fixes: ca4419f15abd ("xsk: Add launch time hardware offload support to XDP Tx metadata") Cc: Cen Zhang (Microsoft) Signed-off-by: Stanislav Fomichev Link: https://patch.msgid.link/20260727161959.885642-7-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- .../net/ethernet/mellanox/mlx5/core/en/xdp.c | 5 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +- include/net/libeth/xsk.h | 2 +- include/net/xdp_sock_drv.h | 51 ++++++++++--------- net/xdp/xsk_buff_pool.c | 6 +-- 6 files changed, 37 insertions(+), 33 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index beaea1479485..16fcc8cf6191 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3082,7 +3082,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) meta_req.tx_buffer = bi; meta_req.meta = meta; meta_req.used_desc = 0; - xsk_tx_metadata_request(&meta, &igc_xsk_tx_metadata_ops, + xsk_tx_metadata_request(pool, &meta, &igc_xsk_tx_metadata_ops, &meta_req); /* xsk_tx_metadata_request() may have updated next_to_use */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index dac5e9d4c8bd..77ea51bfbaae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -505,7 +505,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx */ mlx5e_xdp_mpwqe_session_start(sq); if (meta) - xsk_tx_metadata_request(meta, + xsk_tx_metadata_request(sq->xsk_pool, meta, &mlx5e_xsk_tx_metadata_ops, &session->wqe->eth); } @@ -653,7 +653,8 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, sq->pc += num_wqebbs; if (meta) - xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg); + xsk_tx_metadata_request(sq->xsk_pool, meta, + &mlx5e_xsk_tx_metadata_ops, eseg); sq->doorbell_cseg = cseg; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7c3a7c56a81a..97b28cfa14c2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2748,8 +2748,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) meta_req.set_ic = &set_ic; meta_req.tbs = tx_q->tbs; meta_req.edesc = &tx_q->dma_entx[entry]; - xsk_tx_metadata_request(&meta, &stmmac_xsk_tx_metadata_ops, - &meta_req); + xsk_tx_metadata_request(pool, &meta, + &stmmac_xsk_tx_metadata_ops, &meta_req); if (set_ic) { tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, tx_desc); diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h index e2fa6bf6b1b3..5dcc0d7f65b7 100644 --- a/include/net/libeth/xsk.h +++ b/include/net/libeth/xsk.h @@ -205,7 +205,7 @@ __libeth_xsk_xmit_fill_buf_md(const struct xdp_desc *xdesc, BUILD_BUG_ON(!__builtin_constant_p(tmo == libeth_xsktmo)); tmo = tmo == libeth_xsktmo ? &__libeth_xsktmo : tmo; - xsk_tx_metadata_request(&ctx.meta, tmo, &desc); + xsk_tx_metadata_request(sq->pool, &ctx.meta, tmo, &desc); return desc; } diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index f87c4215673e..b344789f5df8 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -245,7 +245,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) * details. * * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata - * pointer, if it is present and valid (initialized to %NULL otherwise). + * pointer, if it is present (initialized to %NULL otherwise). */ static inline struct xdp_desc_ctx xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) @@ -274,54 +274,56 @@ xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool, /** * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission * and call appropriate xsk_tx_metadata_ops operation. + * @pool: pointer to AF_XDP buffer pool, used to validate the metadata * @pmeta: pointer to pointer to AF_XDP metadata area * @ops: pointer to struct xsk_tx_metadata_ops - * @priv: pointer to driver-private aread + * @priv: pointer to driver-private area * * This function should be called by the networking device when * it prepares AF_XDP egress packet. */ -static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, - const struct xsk_tx_metadata_ops *ops, - void *priv) +static inline void +xsk_tx_metadata_request(const struct xsk_buff_pool *pool, + struct xsk_tx_metadata **pmeta, + const struct xsk_tx_metadata_ops *ops, void *priv) { const struct xsk_tx_metadata *meta = *pmeta; + u64 flags; if (!meta) return; + if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) { + *pmeta = NULL; + return; /* no way to signal the error to the user */ + } + if (ops->tmo_request_launch_time) - if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) - ops->tmo_request_launch_time(meta->request.launch_time, - priv); + if (flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + ops->tmo_request_launch_time( + READ_ONCE(meta->request.launch_time), priv); if (ops->tmo_request_timestamp) - if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) + if (flags & XDP_TXMD_FLAGS_TIMESTAMP) ops->tmo_request_timestamp(priv); if (ops->tmo_request_checksum) - if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) - ops->tmo_request_checksum(meta->request.csum_start, - meta->request.csum_offset, priv); + if (flags & XDP_TXMD_FLAGS_CHECKSUM) + ops->tmo_request_checksum( + READ_ONCE(meta->request.csum_start), + READ_ONCE(meta->request.csum_offset), priv); - if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)) + if (!(flags & XDP_TXMD_FLAGS_TIMESTAMP)) *pmeta = NULL; } static inline struct xsk_tx_metadata * __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data) { - struct xsk_tx_metadata *meta; - u64 flags; - if (!pool->tx_metadata_len) return NULL; - meta = data - pool->tx_metadata_len; - if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) - return NULL; /* no way to signal the error to the user */ - - return meta; + return data - pool->tx_metadata_len; } static inline struct xsk_tx_metadata * @@ -520,9 +522,10 @@ xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool, return false; } -static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta, - const struct xsk_tx_metadata_ops *ops, - void *priv) +static inline void +xsk_tx_metadata_request(const struct xsk_buff_pool *pool, + struct xsk_tx_metadata **pmeta, + const struct xsk_tx_metadata_ops *ops, void *priv) { } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index a4089480b22b..78c14f106395 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -765,11 +765,11 @@ EXPORT_SYMBOL(xp_raw_get_dma); * @addr: desc address (from userspace) * * Helper for getting desc's DMA address and metadata pointer, if present. - * Saves one call on hotpath, double calculation of the actual address, - * and inline checks for metadata presence and sanity. + * Saves one call on hotpath and double calculation of the actual address. + * Metadata is validated later by xsk_tx_metadata_request(). * * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata - * pointer, if it is present and valid (initialized to %NULL otherwise). + * pointer, if it is present (initialized to %NULL otherwise). */ struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) { From 1f428e30947395d9b9aacee03e25a4e6cfcad7a4 Mon Sep 17 00:00:00 2001 From: Yi Cong Date: Wed, 29 Jul 2026 11:04:36 +0800 Subject: [PATCH 050/116] net: usb: ax88179_178a: fix skb leak in ax88179_tx_fixup() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the interface has NETIF_F_SG enabled and skb_linearize() fails in ax88179_tx_fixup(), the function returns NULL without freeing the skb. usbnet_start_xmit() treats a NULL return from tx_fixup() as a drop (info->flags does not set FLAG_MULTI_PACKET for this driver), jumping to the "drop" label where it does `if (skb) dev_kfree_skb_any(skb)`. Because tx_fixup() returned NULL, the local skb variable in usbnet_start_xmit() is NULL, so the original skb is never freed — a memory leak on every TX frame whose linearization fails (i.e. under memory pressure). Free the skb before returning, matching the error handling already used for the pskb_expand_head() failure path in the same function. Fixes: 16b1c4e01c89 ("net: usb: ax88179_178a: add TSO feature") Cc: stable@vger.kernel.org Signed-off-by: Yi Cong Link: https://patch.msgid.link/20260729030436.3420477-1-cong.yi@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/usb/ax88179_178a.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 98f899ea2e94..81d8412ce8e2 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1487,8 +1487,10 @@ ax88179_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) headroom = skb_headroom(skb) - 8; - if ((dev->net->features & NETIF_F_SG) && skb_linearize(skb)) + if ((dev->net->features & NETIF_F_SG) && skb_linearize(skb)) { + dev_kfree_skb_any(skb); return NULL; + } if ((skb_header_cloned(skb) || headroom < 0) && pskb_expand_head(skb, headroom < 0 ? 8 : 0, 0, GFP_ATOMIC)) { From 1cb4298810e27e037d3ca07286ecbb97e89ba58d Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Fri, 31 Jul 2026 12:22:59 -0700 Subject: [PATCH 051/116] bnge: Fix NULL pointer dereference in aux device release If allocation of auxr_dev fails during auxiliary device setup, the error path calls auxiliary_device_uninit(), which eventually invokes bnge_aux_dev_release(). The release callback unconditionally dereferences aux_priv->auxr_dev->pdev to retrieve the parent bnge_dev. Since auxr_dev has not yet been allocated on this failure path, the dereference results in a NULL pointer exception Retrieve the parent bnge_dev from the auxiliary device's parent instead of auxr_dev, and free auxr_dev only when it was successfully allocated. This allows the release callback to correctly clean up partially initialized auxiliary devices. Fixes: 8ac050ec3b1c ("bng_en: Add RoCE aux device support") Signed-off-by: Alok Tiwari Reviewed-by: Bhargava Marreddy Link: https://patch.msgid.link/20260731192301.1427645-1-alok.a.tiwari@oracle.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnge/bnge_auxr.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c index 67e93e17d4d9..0955b488b6fe 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c @@ -141,12 +141,15 @@ static void bnge_aux_dev_release(struct device *dev) { struct bnge_auxr_priv *aux_priv = container_of(dev, struct bnge_auxr_priv, aux_dev.dev); - struct bnge_dev *bd = pci_get_drvdata(aux_priv->auxr_dev->pdev); + struct bnge_auxr_dev *auxr_dev = aux_priv->auxr_dev; + struct bnge_dev *bd = pci_get_drvdata(to_pci_dev(dev->parent)); ida_free(&bnge_aux_dev_ids, aux_priv->id); - kfree(aux_priv->auxr_dev->auxr_info); + if (auxr_dev) { + kfree(auxr_dev->auxr_info); + kfree(auxr_dev); + } bd->auxr_dev = NULL; - kfree(aux_priv->auxr_dev); kfree(aux_priv); bd->aux_priv = NULL; } From 5d9686af2976741bbd79b150d1c9e60b81e7f12e Mon Sep 17 00:00:00 2001 From: Daming Li Date: Thu, 30 Jul 2026 22:55:52 +0800 Subject: [PATCH 052/116] net: smc: fix splice entry lifetime imbalance in smc_rx_splice smc_rx_splice() passes pages to splice_to_pipe() before taking the references that cover the lifetime of each splice entry. In the VM-backed RMB path, splice_to_pipe() may drop unqueued entries through smc_rx_spd_release(), while queued entries are released later via the pipe buffer callback. The old post-splice accounting also derives the number of queued VM pages from an offset mutated while building the descriptor, and a multi-page splice pairs one sock_hold() with multiple sock_put() calls. Take the page and socket references for every candidate entry before splice_to_pipe(), and drop the matching private state, page reference, and socket reference from smc_rx_spd_release() for entries that never get queued. This fixes a refcount imbalance that can underflow page refcounts and trigger a use-after-free. Fixes: 9014db202cb7 ("smc: add support for splice()") Cc: stable@vger.kernel.org Reported-by: Vega Co-developed-by: Xiao Liu Signed-off-by: Xiao Liu Signed-off-by: Daming Li Signed-off-by: Ren Wei Reviewed-by: Dust Li Reviewed-by: Sidraya Jayagond Link: https://patch.msgid.link/20260730145552.360287-2-enjou1224z@gmail.com Signed-off-by: Jakub Kicinski --- net/smc/smc_rx.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index c1d9b923938d..5c9e4d8b57de 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -150,7 +150,12 @@ static const struct pipe_buf_operations smc_pipe_ops = { static void smc_rx_spd_release(struct splice_pipe_desc *spd, unsigned int i) { + struct smc_spd_priv *priv = (struct smc_spd_priv *)spd->partial[i].private; + struct sock *sk = &priv->smc->sk; + + kfree(priv); put_page(spd->pages[i]); + sock_put(sk); } static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, @@ -209,6 +214,10 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, offset = 0; } } + for (i = 0; i < nr_pages; i++) { + get_page(pages[i]); + sock_hold(&smc->sk); + } spd.nr_pages_max = nr_pages; spd.nr_pages = nr_pages; spd.pages = pages; @@ -217,16 +226,8 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, spd.spd_release = smc_rx_spd_release; bytes = splice_to_pipe(pipe, &spd); - if (bytes > 0) { - sock_hold(&smc->sk); - if (!lgr->is_smcd && smc->conn.rmb_desc->is_vm) { - for (i = 0; i < PAGE_ALIGN(bytes + offset) / PAGE_SIZE; i++) - get_page(pages[i]); - } else { - get_page(smc->conn.rmb_desc->pages); - } + if (bytes > 0) atomic_add(bytes, &smc->conn.splice_pending); - } kfree(priv); kfree(partial); kfree(pages); From 4ff9548d84945d2cbf9e4c207288063a200ea397 Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Thu, 30 Jul 2026 12:59:26 +0000 Subject: [PATCH 053/116] ipv4: Fix fib_nlmsg_size() for RTA_VIA nexthops fib_nlmsg_size() still estimates nexthop space as if every gateway is encoded as an IPv4 RTA_GATEWAY attribute. IPv4 routes can also carry an IPv6 gateway, which fib_nexthop_info() dumps as RTA_VIA. As a result, route notifications can allocate an skb that is too small. fib_dump_info() then fails with -EMSGSIZE and rtmsg_fib() hits the WARN_ON() that marks such failures as a fib_nlmsg_size() bug. With panic_on_warn set, this becomes a kernel panic. Mirror the actual nexthop dump layout in fib_nlmsg_size(): account for IPv6 nexthop gateways dumped as RTA_VIA, for the no-header rtnexthop layout used inside RTA_MULTIPATH, and for RTA_FLOW only when it is actually present. Fixes: d15662682db2 ("ipv4: Allow ipv6 gateway with ipv4 routes") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zihan Xi Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/6f53fa797fcaeb26966432ed7ae9bb87c4961f37.1785411220.git.zihanx@nebusec.ai Signed-off-by: Jakub Kicinski --- net/ipv4/fib_semantics.c | 67 +++++++++++++++++++++++++++++----------- 1 file changed, 49 insertions(+), 18 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 4f3c0740dde9..78f84ae3ee12 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -490,6 +490,34 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) return -1; } +static size_t fib_nexthop_nlmsg_size(const struct fib_nh_common *nhc, + bool skip_oif) +{ + size_t nhsize = 0; + + switch (nhc->nhc_gw_family) { + case AF_INET: + nhsize += nla_total_size(4); /* RTA_GATEWAY */ + break; + case AF_INET6: + nhsize += nla_total_size(sizeof(struct rtvia) + + sizeof(struct in6_addr)); + break; + } + + if (!skip_oif && nhc->nhc_dev) + nhsize += nla_total_size(4); /* RTA_OIF */ + + if (nhc->nhc_lwtstate) { + /* RTA_ENCAP */ + nhsize += lwtunnel_get_encap_size(nhc->nhc_lwtstate); + /* RTA_ENCAP_TYPE */ + nhsize += nla_total_size(2); + } + + return nhsize; +} + size_t fib_nlmsg_size(struct fib_info *fi) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) @@ -507,32 +535,35 @@ size_t fib_nlmsg_size(struct fib_info *fi) payload += nla_total_size(4); /* RTA_NH_ID */ if (nhs) { - size_t nh_encapsize = 0; - /* Also handles the special case nhs == 1 */ - - /* each nexthop is packed in an attribute */ - size_t nhsize = nla_total_size(sizeof(struct rtnexthop)); + size_t mpsize = 0; unsigned int i; - /* may contain flow and gateway attribute */ - nhsize += 2 * nla_total_size(4); - - /* grab encap info */ for (i = 0; i < fib_info_num_path(fi); i++) { struct fib_nh_common *nhc = fib_info_nhc(fi, i); + size_t nhsize; - if (nhc->nhc_lwtstate) { - /* RTA_ENCAP_TYPE */ - nh_encapsize += lwtunnel_get_encap_size( - nhc->nhc_lwtstate); - /* RTA_ENCAP */ - nh_encapsize += nla_total_size(2); + nhsize = fib_nexthop_nlmsg_size(nhc, nhs != 1); + + if (nhs != 1) + nhsize += NLA_ALIGN(sizeof(struct rtnexthop)); + +#ifdef CONFIG_IP_ROUTE_CLASSID + if (nhc->nhc_family == AF_INET) { + struct fib_nh *nh; + + nh = container_of(nhc, struct fib_nh, nh_common); + if (nh->nh_tclassid) + nhsize += nla_total_size(4); } +#endif + if (nhs == 1) + payload += nhsize; + else + mpsize += nhsize; } - /* all nexthops are packed in a nested attribute */ - payload += nla_total_size((nhs * nhsize) + nh_encapsize); - + if (nhs != 1) + payload += nla_total_size(mpsize); } return payload; From d141f087b1af656f055d7c5793a3e87817ba0bbe Mon Sep 17 00:00:00 2001 From: Hidayath Khan Date: Thu, 30 Jul 2026 16:22:16 +0200 Subject: [PATCH 054/116] s390/qeth: validate user buffer length in SNMP and ARP query ioctls qeth_snmp_command() and qeth_l3_arp_query() allocate a buffer sized by a user-supplied length (udata_len) without checking a lower bound, then set udata_offset to a fixed non-zero value and pass both to a reply callback. The callback bounds-checks the copy with if ((udata_len - udata_offset) < len) Both fields are u32, so a udata_len smaller than udata_offset makes the subtraction wrap and the check pass, and the following memcpy() writes past the allocation. A udata_len of 0 also yields ZERO_SIZE_PTR from kzalloc(), which the existing NULL check does not catch. Reject buffers smaller than udata_offset before allocating, so the callback subtraction can no longer underflow. Fixes: 4a71df50047f ("qeth: new qeth device driver") Cc: stable@vger.kernel.org Reviewed-by: Alexandra Winter Signed-off-by: Hidayath Khan Reviewed-by: Joe Damato Link: https://patch.msgid.link/20260730142216.218309-1-hidayath@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/s390/net/qeth_core_main.c | 3 +++ drivers/s390/net/qeth_l3_main.c | 5 +++++ 2 files changed, 8 insertions(+) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index f18eed9df3c7..c3257b213360 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4710,6 +4710,9 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata) if (req_len > QETH_BUFSIZE) return -EINVAL; + if (qinfo.udata_len < sizeof(struct qeth_snmp_ureq_hdr)) + return -EINVAL; + iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_SNMP_CONTROL, req_len); if (!iob) return -ENOMEM; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 1542bfc9f561..f1ac9950dcb4 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1415,6 +1415,11 @@ static int qeth_l3_arp_query(struct qeth_card *card, char __user *udata) rc = -EFAULT; goto out; } + + if (qinfo.udata_len < QETH_QARP_ENTRIES_OFFSET) { + rc = -EINVAL; + goto out; + } qinfo.udata = kzalloc(qinfo.udata_len, GFP_KERNEL); if (!qinfo.udata) { rc = -ENOMEM; From d0f86fb36eb260abd10007b62c9dcc1028e03e61 Mon Sep 17 00:00:00 2001 From: Xuanqiang Luo Date: Thu, 30 Jul 2026 17:35:54 +0800 Subject: [PATCH 055/116] udp: fix potential use-after-free in tunnel segmentation __skb_udp_tunnel_segment() gets the UDP header before ensuring the tunnel header is in the skb head. If the pull reallocates skb->head, the saved UDP header pointer is no longer valid. Get the UDP header after the pull to avoid a potential use-after-free. Fixes: dbef491ebe7f ("udp: Use uh->len instead of skb->len to compute checksum in segmentation") Signed-off-by: Xuanqiang Luo Reviewed-by: Antoine Tenart Link: https://patch.msgid.link/20260730093554.68127-1-xuanqiang.luo@linux.dev Signed-off-by: Jakub Kicinski --- net/ipv4/udp_offload.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 29651b1a0bc7..abcd3cc2d9a3 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -178,17 +178,19 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); - struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; + struct udphdr *uh; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; + uh = udp_hdr(skb); + /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the From 2a33516f9ef59ad11844d4fc152f889449b5daf3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Wed, 29 Jul 2026 21:14:16 +0200 Subject: [PATCH 056/116] net/sched: sch_cake: drop WARN_ON(1) for malformed packets in ACK filter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The sch_cake ACK filter parses packets to find the TCP header and filter duplicated ACKs if the flow is backlogged. The parsing code contains a WARN_ON(1) which can be triggered by a malformed IP header in certain cases. Depending on the system configuration, this leads either to either spamming dmesg with warnings, or a panic if panic_on_warn is set. The code already correctly skips the offending packet in the branch that triggers the warning, so the WARN_ON itself doesn't really serve any purpose. So just drop it altogether to avoid the inconvenient side effects. Fixes: 8b7138814f29 ("sch_cake: Add optional ACK filter") Reported-by: Zhiling Zou Reported-by: Ren Wei Signed-off-by: Toke Høiland-Jørgensen Link: https://patch.msgid.link/20260729191417.45665-1-toke@toke.dk Signed-off-by: Jakub Kicinski --- net/sched/sch_cake.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index f64be54ead49..f25f60978631 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1287,7 +1287,6 @@ static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, seglen = ipv6_payload_len(skb, ipv6h_check); } else { - WARN_ON(1); /* shouldn't happen */ continue; } From 1a35da325cac4d5bcad76a2aa943408a6f1d9000 Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Wed, 29 Jul 2026 09:16:53 +0000 Subject: [PATCH 057/116] packet: synchronize pressure clearing with ring reconfiguration packet_set_ring() updates the RX ring state under sk_receive_queue.lock, but used to publish the tpacket receive mode through po->prot_hook.func after releasing that lock. packet_poll() and packet_recvmsg() can then run the pressure clearing path after the ring has been cleared while still seeing tpacket_rcv, causing __packet_rcv_has_room() to dereference stale or NULL ring storage. Move the existing receive hook assignment into the same sk_receive_queue.lock section as the ring state update. Keep the assignment otherwise unchanged, including on TX ring reconfiguration, to avoid adding behavior changes that are not required for the fix. Serialize packet_recvmsg() pressure clearing with the same queue lock only after PACKET_SOCK_PRESSURE has been observed. If the flag is clear and the socket has moved away from tpacket_rcv, packet_set_ring() has already detached the socket and waited for synchronize_net(), so no new packet input can set the flag again. packet_poll() already holds sk_receive_queue.lock, so it uses the new unlocked helper directly. Fixes: 2ccdbaa6d55b ("packet: rollover lock contention avoidance") Cc: stable@vger.kernel.org Reported-by: Vega Assisted-by: Codex:gpt-5.4 Signed-off-by: Zihan Xi Link: https://patch.msgid.link/f90b5688311fa278d1361ea8c6be0bf25967d591.1785247446.git.zihanx@nebusec.ai Signed-off-by: Paolo Abeni --- net/packet/af_packet.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5ae0511e89e3..0e1355be89f6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1315,13 +1315,25 @@ static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) return ret; } -static void packet_rcv_try_clear_pressure(struct packet_sock *po) +static void __packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } +static void packet_rcv_try_clear_pressure(struct packet_sock *po) +{ + struct sock *sk = &po->sk; + + if (!packet_sock_flag(po, PACKET_SOCK_PRESSURE)) + return; + + spin_lock_bh(&sk->sk_receive_queue.lock); + __packet_rcv_try_clear_pressure(po); + spin_unlock_bh(&sk->sk_receive_queue.lock); +} + static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); @@ -4305,7 +4317,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } - packet_rcv_try_clear_pressure(po); + __packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { @@ -4545,14 +4557,14 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; + po->prot_hook.func = (po->rx_ring.pg_vec) ? + tpacket_rcv : packet_rcv; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; - po->prot_hook.func = (po->rx_ring.pg_vec) ? - tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", From cf6f8b29befb92173659bcef6a441d274947bfae Mon Sep 17 00:00:00 2001 From: "Cen Zhang (Microsoft)" Date: Thu, 30 Jul 2026 18:20:06 -0400 Subject: [PATCH 058/116] net/openvswitch: check Ethernet header length in key_extract() When a packet arrives on an ARPHRD_NONE device (e.g. TUN), ovs_flow_key_extract() trusts the user-provided skb->protocol field: if it is ETH_P_TEB, the packet is classified as MAC_PROTO_ETHERNET and key_extract() is called without ensuring the skb has ETH_HLEN (14) bytes of linear data. key_extract() unconditionally pulls 2 * ETH_ALEN bytes for MAC addresses and parse_ethertype() pulls 2 more, either of which triggers a kernel BUG in __skb_pull() when the linear area is too small. kernel BUG at include/linux/skbuff.h:2848! RIP: 0010:key_extract+0xa7e/0xd90 net/openvswitch/flow.c:933 ovs_flow_key_extract+0x419/0xa70 ovs_vport_receive+0x222/0x390 netdev_frame_hook+0x3e0/0x630 tun_get_user+0x2d0c/0x38e0 Fixed by calling check_header() in key_extract() before accessing the Ethernet header. Fixes: 217ac77a3c25 ("openvswitch: allow L3 netdev ports") Reported-by: AutonomousCodeSecurity@microsoft.com Reviewed-by: Eelco Chaudron Signed-off-by: Cen Zhang (Microsoft) Reviewed-by: Ilya Maximets Link: https://patch.msgid.link/20260730222006.118652-1-blbllhy@gmail.com Signed-off-by: Paolo Abeni --- net/openvswitch/flow.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 66366982f604..46c1d66aad8c 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -889,8 +889,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * Ethernet header * @key: output flow key * - * The caller must ensure that skb->len >= ETH_HLEN. - * * Initializes @skb header fields as follows: * * - skb->mac_header: the L2 header. @@ -910,8 +908,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) */ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) { - struct ethhdr *eth; - /* Flags are always used as part of stats */ key->tp.flags = 0; @@ -926,6 +922,13 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) skb_reset_network_header(skb); key->eth.type = skb->protocol; } else { + struct ethhdr *eth; + int err; + + err = check_header(skb, ETH_HLEN); + if (unlikely(err)) + return err; + eth = eth_hdr(skb); ether_addr_copy(key->eth.src, eth->h_source); ether_addr_copy(key->eth.dst, eth->h_dest); From a347304b2ca1a5377d5bd2d8a72e4b4f12afe648 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 1 Aug 2026 08:56:32 -0400 Subject: [PATCH 059/116] net/sched: cls_api: Always acquire rtnl_lock when destroying locked classifiers Another challenge with unlocked filters. There is a short window in tc_new_tfilter where a tcf_proto can be found and briefly referenced by a totally unrelated, unlocked classifier's request and cause a race. Feng created a poc which created this race with two threads, one creating a u32 filter and other a flower filter in the same chain/prio: 1. Both threads enter tc_new_tfilter, both find the chain empty, both drop filter_chain_lock 2. u32 finishes tcf_proto_create("u32") first, calls tcf_chain_tp_insert_unique() -> inserts u32_tp into the chain 3. flower finishes tcf_proto_create("flower") later, calls tcf_chain_tp_insert_unique() -> tcf_chain_tp_find() now sees u32_tp already there, takes a reference on it, destroys flower's own tp_new and returns u32_tp to the caller. Flower then hits the kind mismatch check (because it requested for kind "flower" but tp->ops->kind is "u32") and goes through the errout path which calls tcf_proto_put() on u32_tp. If the u32 thread has already gone through its own errout (its change() call failed on the PoC's empty options) and dropped its create and insert refs, flower's put is the last one and drops u32_tp's refcnt to zero. At this point tp->ops->destroy() runs in a context that never took rtnl_lock. When that happens, it might cause a UAF like the following (illustrated by the PoC): [ +0.000710] BUG: KASAN: slab-use-after-free in u32_init (net/sched/cls_u32.c:393) [ +0.000281] Read of size 8 at addr ffff888120022f00 by task poc_feng_xue/524 Call Trace: u32_init (net/sched/cls_u32.c:393) tc_new_tfilter (net/sched/cls_api.c:2378) Allocated by task 526: u32_init (net/sched/cls_u32.c:378) tc_new_tfilter (net/sched/cls_api.c:2378) Freed by task 522: kfree u32_destroy (net/sched/cls_u32.c:662) tcf_proto_destroy (net/sched/cls_api.c:446) tcf_proto_put (net/sched/cls_api.c:459) tc_new_tfilter (net/sched/cls_api.c:2459) Fix this by having tcf_proto_destroy() take rtnl_lock around tp->ops->destroy() for locked classifiers whenever rtnl is not held. To explain why I used a temp variable "not_lockless" I'd like to point to a semi-related note on rtnl_held vs TCF_PROTO_OPS_DOIT_UNLOCKED (adding here for future cleanup if deemed necessary): The rtnl_held parameter and the TCF_PROTO_OPS_DOIT_UNLOCKED flag are redundant sources of truth for whether rtnl_lock is held. Among the nine classifier destroy(..rtnl_held..) callbacks, only flower consults the rtnl_held parameter which it propagates to tc_setup_cb_destroy() and tc_setup_cb_call(). The other eight (u32, flow, bpf, cgroup, route, basic, fw, mall) ignore it entirely;-> those that call tc_setup_cb_destroy() (u32, bpf, mall) hardcode true always instead of forwarding the parameter. A future cleanup should remove the rtnl_held parameter from the destroy callback signature entirely and have callers rely solely on their knowledge whether they are running in an unlocked context. Fixes: 12db03b65c2b ("net: sched: extend proto ops to support unlocked classifiers") Reported-by: Feng Xue Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260801125632.360365-1-jhs@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/cls_api.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index fee4524adc98..4e6a2812a4f3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -443,7 +443,22 @@ static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, bool sig_destroy, struct netlink_ext_ack *extack) { - tp->ops->destroy(tp, rtnl_held, extack); + /* A locked classifier's destroy callback (e.g. u32_destroy) uses + * rtnl_dereference() and mutates shared structures (e.g. the + * tc_u_common hash list) that are only safe under rtnl_lock. When an + * unlocked classifier's request (e.g. flower on ingress) loses the + * tcf_chain_tp_insert_unique() race and ends up dropping the last + * reference on a locked classifier's proto, destroy() would run + * without rtnl held. Take it here in that case. + */ + bool not_lockless = !rtnl_held && + !(tp->ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED); + + if (not_lockless) + rtnl_lock(); + tp->ops->destroy(tp, rtnl_held || not_lockless, extack); + if (not_lockless) + rtnl_unlock(); tcf_proto_count_usesw(tp, false); if (sig_destroy) tcf_proto_signal_destroyed(tp->chain, tp); From 0e243671bc7b8eaf00f83dd2f4367436dc0cff98 Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Mon, 3 Aug 2026 12:27:57 +0000 Subject: [PATCH 060/116] ipv6: prevent in6_dev_get() from resurrecting inet6_dev in6_dev_get() reads dev->ip6_ptr under RCU and then unconditionally increments its refcount. Device teardown can clear the pointer and drop the last reference between these operations. The increment then resurrects an object whose RCU free has already been queued, so callers can use it after it is freed. Use refcount_inc_not_zero() and return NULL when the object has already reached zero. RCU keeps the memory accessible through the attempted reference acquisition, and a successful increment pins the object for the caller. An independent run on the exact unpatched 6f5156d7a31a (v7.2-rc3) kernel reproduced the invalid reference acquisition as UID 1000: refcount_t: addition on 0; use-after-free. ip6_mc_source+0xef4/0x17e0 It was followed by the corresponding reference underflow in ip6_mc_source(). The supplied trace from the same unpatched revision additionally shows the access after the RCU read-side section ends: BUG: KASAN: slab-use-after-free in mutex_lock+0x76/0xe0 Write of size 8 at addr ffff888015b50240 by task poc/1219 Bug found and triaged by OpenAI Security Research and validated by Trail of Bits. Fixes: 8814c4b53381 ("[IPV6] ADDRCONF: Convert addrconf_lock to RCU.") Cc: stable@vger.kernel.org Signed-off-by: Kyle Zeng Co-developed-by: David Lee Signed-off-by: David Lee Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260803122758.666112-1-david.lee@trailofbits.com Signed-off-by: Jakub Kicinski --- include/net/addrconf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 8ced27a8229b..e6764245995f 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -405,8 +405,8 @@ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev) rcu_read_lock(); idev = rcu_dereference(dev->ip6_ptr); - if (idev) - refcount_inc(&idev->refcnt); + if (idev && !refcount_inc_not_zero(&idev->refcnt)) + idev = NULL; rcu_read_unlock(); return idev; } From 06232cb44bc8e81adc2f1d40a01bed830b607ea2 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Mon, 3 Aug 2026 11:51:56 +0200 Subject: [PATCH 061/116] net: stmmac: resume PHY before hardware setup when opening the interface Since the referenced commit, changing the MTU on a running interface no longer disconnects and reconnects the PHY; __stmmac_release() merely stops phylink, which also suspends the PHY (BMCR power-down) when WoL is not enabled. __stmmac_open() then performs the DMA software reset in stmmac_hw_setup() before phylink_start() resumes the PHY again. IEEE 802.3 22.2.4.1.5 allows a PHY to stop its receive clock while powered down, and stmmac requires a running receive clock for the DMA software reset to complete (the phylink config sets mac_requires_rxc). On such setups, e.g. the RK3566-based Home Assistant Green with an RTL8211F-VD PHY in RGMII mode, any runtime MTU change now times out and leaves the interface dead: rk_gmac-dwmac fe010000.ethernet end0: Failed to reset the dma rk_gmac-dwmac fe010000.ethernet end0: stmmac_hw_setup: DMA engine initialization failed rk_gmac-dwmac fe010000.ethernet end0: __stmmac_open: Hw setup failed rk_gmac-dwmac fe010000.ethernet end0: failed reopening the interface after MTU change In the field this is triggered by NetworkManager applying an MTU while activating the connection, breaking networking entirely. The same regression has also been reported on i.MX8MP and reproduced on SoCFPGA based systems. Resume the PHY in __stmmac_open() before the hardware setup, making it the counterpart of the phylink_stop() in __stmmac_release(), like stmmac_resume() already does for the same reason. phylink_start() also resumes the PHY, but only after stmmac_hw_setup(), and it cannot be moved before the hardware setup since it may bring the link up immediately from a workqueue, racing with the initialization (see the comment in stmmac_resume()). For the regular ndo_open path the PHY has just been attached and is not suspended, in which case phylink_prepare_resume() does nothing. Fixes: db299a0c09e9 ("net: stmmac: move PHY handling out of __stmmac_open()/release()") Link: https://github.com/home-assistant/operating-system/issues/4858 Tested-by: Alexander Stein Signed-off-by: Stefan Agner Tested-by: Maxime Chevallier Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20260803095156.132827-1-stefan@agner.ch Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 97b28cfa14c2..a71f0df26378 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4134,6 +4134,15 @@ static int __stmmac_open(struct net_device *dev, dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs; memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf)); + /* The PHY is suspended when the interface is reopened without + * disconnecting the PHY, e.g. on MTU change. IEEE 802.3 allows PHYs + * to stop their receive clock while powered down, but the DMA + * software reset in stmmac_hw_setup() requires a running receive + * clock, and phylink_start() below resumes the PHY only after the + * hardware setup. Resume a suspended PHY here first. + */ + phylink_prepare_resume(priv->phylink); + stmmac_reset_queues_param(priv); ret = stmmac_hw_setup(dev); From 452636ea5410a96e02ebaaf80b21e3620b98e0dd Mon Sep 17 00:00:00 2001 From: Yangyu Chen Date: Sun, 2 Aug 2026 23:46:00 +0800 Subject: [PATCH 062/116] net: atlantic: free stranded TX buffers on ring deinit aq_vec_deinit() drains the TX rings with a single aq_ring_tx_clean() call, which frees at most AQ_CFG_TX_CLEAN_BUDGET (256) descriptors and stops at hw_head, which no longer moves once aq_vec_stop() has stopped the hardware and NAPI. Completed descriptors beyond the budget and everything still posted in [hw_head, sw_tail) keep their skb or xdp_frame when the interface goes down: aq_vec_ring_free() then frees the buffer ring and the references are lost for good. Today this is a silent memory leak on every interface down under TX/XDP_TX load. With the conversion of the RX path to page_pool posted for net-next it becomes much more visible: XDP_TX frames carry fragment references on the RX ring's page_pool, so a single stranded frame keeps the pool's inflight count above zero forever. page_pool_destroy() then never completes, the pool is leaked together with its pages, and "page_pool_release_retry() stalled pool shutdown" is warned every 60 seconds from that point on, on every ifdown, XDP detach or ring resize under XDP_TX load. Bring back aq_ring_tx_deinit() as it was before the removal and use it for teardown again, with one extension: TX rings can hold xdp_frames nowadays, so release those too. They are returned with xdp_return_frame() since this runs in process context. Fixes: eb36bedf28be ("net: aquantia: remove function aq_ring_tx_deinit") Cc: stable@vger.kernel.org # v4.11+ Reviewed-by: Sukhdeep Singh Signed-off-by: Yangyu Chen Acked-by: Mina Almasry Link: https://patch.msgid.link/tencent_EEDC35FAF2750A3A6A0B39BAE0E2C484860A@qq.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/aquantia/atlantic/aq_ring.c | 29 +++++++++++++++++++ .../net/ethernet/aquantia/atlantic/aq_ring.h | 1 + .../net/ethernet/aquantia/atlantic/aq_vec.c | 2 +- 3 files changed, 31 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 8ff07de2bd52..81685a4dc5a6 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -360,6 +360,35 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) return !!budget; } +void aq_ring_tx_deinit(struct aq_ring_s *self) +{ + if (!self) + return; + + for (; self->sw_head != self->sw_tail; + self->sw_head = aq_ring_next_dx(self, self->sw_head)) { + struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head]; + struct device *ndev = aq_nic_get_dev(self->aq_nic); + + if (buff->is_mapped) { + if (buff->is_sop) { + dma_unmap_single(ndev, buff->pa, buff->len, + DMA_TO_DEVICE); + } else { + dma_unmap_page(ndev, buff->pa, buff->len, + DMA_TO_DEVICE); + } + } + + if (buff->is_eop) { + if (buff->skb) + dev_kfree_skb_any(buff->skb); + else if (buff->xdpf) + xdp_return_frame(buff->xdpf); + } + } +} + static void aq_rx_checksum(struct aq_ring_s *self, struct aq_ring_buff_s *buff, struct sk_buff *skb) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index a70b880ada67..6431cc62962f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -202,6 +202,7 @@ void aq_ring_update_queue_state(struct aq_ring_s *ring); void aq_ring_queue_wake(struct aq_ring_s *ring); void aq_ring_queue_stop(struct aq_ring_s *ring); bool aq_ring_tx_clean(struct aq_ring_s *self); +void aq_ring_tx_deinit(struct aq_ring_s *self); int aq_xdp_xmit(struct net_device *dev, int num_frames, struct xdp_frame **frames, u32 flags); int aq_ring_rx_clean(struct aq_ring_s *self, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index 2f9033ceed8c..05814fea0f5f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -275,7 +275,7 @@ void aq_vec_deinit(struct aq_vec_s *self) for (i = 0U; self->tx_rings > i; ++i) { ring = self->ring[i]; - aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); + aq_ring_tx_deinit(&ring[AQ_VEC_TX_ID]); aq_ring_rx_deinit(&ring[AQ_VEC_RX_ID]); } From e8e7471ef686b6c002218fee9671cc61992ae01a Mon Sep 17 00:00:00 2001 From: Yangyu Chen Date: Sun, 2 Aug 2026 23:46:38 +0800 Subject: [PATCH 063/116] net: atlantic: free RX pages of consumed but not refilled buffers aq_ring_rx_deinit() only walks [sw_head, sw_tail), the region posted to hardware. Since the page reuse strategy was added, a cleaned RX buffer keeps its page (and its DMA mapping) in the ring for reuse, and refill is batched: aq_ring_rx_fill() returns early until AQ_CFG_RX_REFILL_THRES slots are free. Slots that were consumed but not yet reposted therefore sit in the complementary [sw_tail, sw_head) gap with a live page, and the deinit walk never visits them: up to a refill batch worth of pages and DMA mappings leak on every interface down. Walk the whole ring instead and release whatever is still there. Also bail out if the buffer ring is already gone: a partial aq_ptp_ring_alloc() failure frees the ring but leaves aq_nic set, so aq_ptp_ring_deinit() still gets here on the unwind path. Cc: stable@vger.kernel.org # v5.2+ Fixes: 46f4c29d9de6 ("net: aquantia: optimize rx performance by page reuse strategy") Reviewed-by: Sukhdeep Singh Signed-off-by: Yangyu Chen Acked-by: Mina Almasry Link: https://patch.msgid.link/tencent_607CBA8237DA438E36B844318B21538DE008@qq.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/aquantia/atlantic/aq_ring.c | 22 +++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 81685a4dc5a6..e1193c6719d9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -950,15 +950,29 @@ int aq_ring_rx_fill(struct aq_ring_s *self) void aq_ring_rx_deinit(struct aq_ring_s *self) { - if (!self) + unsigned int i; + + if (!self || !self->buff_ring) return; - for (; self->sw_head != self->sw_tail; - self->sw_head = aq_ring_next_dx(self, self->sw_head)) { - struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head]; + /* Release every page still owned by the ring. + * + * Walking [sw_head, sw_tail) is not enough: refill is batched + * (aq_ring_rx_fill() waits for AQ_CFG_RX_REFILL_THRES free slots), + * so slots that were cleaned but not yet reposted accumulate in the + * [sw_tail, sw_head) gap, and they keep their page for reuse. Walk + * the whole ring and release whatever is left. + */ + for (i = 0; i < self->size; i++) { + struct aq_ring_buff_s *buff = &self->buff_ring[i]; + + if (!buff->rxdata.page) + continue; aq_free_rxpage(&buff->rxdata, aq_nic_get_dev(self->aq_nic)); } + + self->sw_head = self->sw_tail; } void aq_ring_free(struct aq_ring_s *self) From 2cbd8a4e5e09aa232a1f8d56ce3d070b18ab2b10 Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Sat, 1 Aug 2026 03:09:20 -0700 Subject: [PATCH 064/116] bnge: use int for bnge_fix_rings_count() return value bnge_fix_rings_count() returns 0 on success or a negative errno on failure However, bnge_adjust_rings() stores its return value in a u16 variable, causing negative error codes such as -ENOMEM to be converted to a large positive value. Use an int for the return code variable so that error values are preserved and propagated correctly. Fixes: 627c67f038d2 ("bng_en: Add resource management support") Signed-off-by: Alok Tiwari Reviewed-by: Bhargava Marreddy Link: https://patch.msgid.link/20260801100923.1498570-1-alok.a.tiwari@oracle.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnge/bnge_resc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_resc.c b/drivers/net/ethernet/broadcom/bnge/bnge_resc.c index 0e94f092813e..4711dd4945ff 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_resc.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_resc.c @@ -163,7 +163,8 @@ static int bnge_adjust_rings(struct bnge_dev *bd, u16 *rx, u16 tx_chunks = bnge_num_tx_to_cp(bd, *tx); if (tx_chunks != *tx) { - u16 tx_saved = tx_chunks, rc; + u16 tx_saved = tx_chunks; + int rc; rc = bnge_fix_rings_count(rx, &tx_chunks, max_nq, sh); if (rc) From 1505b2cb6ae1c7e8ac0c6e4590a204ffc3ab2b24 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Fri, 31 Jul 2026 11:27:11 +0200 Subject: [PATCH 065/116] usbnet: cap max_mtu for drivers without bind callback usbnet_probe() initializes max_mtu to ETH_MAX_MTU and only caps it inside the if (info->bind) block. Drivers without a bind callback never enter this block, so max_mtu stays at ETH_MAX_MTU. QEMU's usb-net device (0x0525/0xa4a2) is claimed by the cdc_subset driver which has no bind callback. The guest accepts any MTU from DHCP (e.g. 65520 from passt), leading to TCP segments that exceed the device's 2048-byte receive buffer and are silently dropped. Initialize max_mtu to net->mtu at probe time and update it inside the bind block. Fixes: f77f0aee4da4 ("net: use core MTU range checking in USB NIC drivers") Cc: jarod@redhat.com Cc: stable@vger.kernel.org Link: https://gitlab.com/qemu-project/qemu/-/issues/3268 Link: https://bugs.passt.top/show_bug.cgi?id=189 Signed-off-by: Laurent Vivier Link: https://patch.msgid.link/20260731092711.857684-1-lvivier@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/usbnet.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 25518635b7b7..a19ecf718f36 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1794,7 +1794,7 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) */ dev->hard_mtu = net->mtu + net->hard_header_len; net->min_mtu = 0; - net->max_mtu = ETH_MAX_MTU; + net->max_mtu = net->mtu; net->netdev_ops = &usbnet_netdev_ops; net->watchdog_timeo = TX_TIMEOUT_JIFFIES; @@ -1804,6 +1804,7 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) // allow device-specific bind/init procedures // NOTE net->name still not usable ... if (info->bind) { + net->max_mtu = ETH_MAX_MTU; status = info->bind(dev, udev); if (status < 0) goto out1; From 5d1c224dd914579524a183a514c12b95095d12ce Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Mon, 3 Aug 2026 08:29:36 +0800 Subject: [PATCH 066/116] net: openvswitch: reallocate update replies for mismatched IDs ovs_flow_cmd_new() preallocates the optional reply skb before it takes ovs_mutex and before it knows which existing flow will be updated. That is normally fine because the skb is sized from the request flow identifier. That identifier also becomes the inserted flow's identifier. For updates, however, a request with a UFID may miss the UFID lookup and then fall back to the flow key lookup. That lookup can legitimately find an existing key-identified flow. UFIDs are optional and the flow key is the primary identifier. For echoed replies, ovs_flow_cmd_fill_info() writes the matched flow's identifier, not the request identifier used for the preallocation. A short request UFID can therefore leave too little room for the key identifier. The fill can then fail with -EMSGSIZE and hit the BUG_ON(error < 0) in the update path. Once the update target has been resolved, reallocate the reply skb if the matched flow needs a larger reply than the request identifier allowed. Do this before replacing the actions so the request can still fail cleanly if the rare extra allocation fails. Fixes: 74ed7ab9264c ("openvswitch: Add support for unique flow IDs.") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zhiling Zou Reviewed-by: Ilya Maximets Link: https://patch.msgid.link/f7bbd3c30ce81a39156e226b3872d73abed21d2f.1785644623.git.zhilinz@nebusec.ai Signed-off-by: Jakub Kicinski --- net/openvswitch/datapath.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index eaf332b156d7..ae69b2cabab9 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1113,9 +1113,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = -EEXIST; goto err_unlock_ovs; } - /* The flow identifier has to be the same for flow updates. - * Look for any overlapping flow. - */ + + /* Look for any overlapping flow. */ if (unlikely(!ovs_flow_cmp(flow, &match))) { if (ovs_identifier_is_key(&flow->id)) flow = ovs_flow_tbl_lookup_exact(&dp->table, @@ -1127,6 +1126,30 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_unlock_ovs; } } + + if (unlikely(reply)) { + size_t cur, req; + + cur = ovs_flow_cmd_msg_size(acts, &new_flow->id, + ufid_flags); + req = ovs_flow_cmd_msg_size(acts, &flow->id, + ufid_flags); + if (cur < req) { + struct sk_buff *resized; + + resized = ovs_flow_cmd_alloc_info(acts, + &flow->id, + info, false, + ufid_flags); + if (IS_ERR(resized)) { + error = PTR_ERR(resized); + goto err_unlock_ovs; + } + kfree_skb(reply); + reply = resized; + } + } + /* Update actions. */ old_acts = ovsl_dereference(flow->sf_acts); rcu_assign_pointer(flow->sf_acts, acts); From e7386770be1bf810bcd6af39d1e4bfeab3408430 Mon Sep 17 00:00:00 2001 From: Bobby Eshleman Date: Mon, 3 Aug 2026 16:47:29 -0700 Subject: [PATCH 067/116] net/mlx5e: fix BQL reset on SQ re-activation mlx5e_queue_start() deactivates and re-activates all channels but closes only the queue being restarted. mlx5e_activate_txqsq() then unconditionally calls netdev_tx_reset_queue(), zeroing the BQL counters of channels that kept their in-flight TX WQEs. The next completion then over-charges and trips the BUG_ON() in dql_completed(): kernel BUG at lib/dynamic_queue_limits.c:99! RIP: 0010:dql_completed+0x23d/0x280 Call Trace: mlx5e_poll_tx_cq+0x668/0xa60 mlx5e_napi_poll+0x5b/0x7b0 net_rx_action+0x15a/0x580 Reset BQL only when the SQ has no bytes in flight (sq->cc == sq->pc). In the case that reset is skipped, the outstanding WQEs will eventually complete and rebalance the dql. The dql->limit is carried across the reset. Fixes: b2588ea40ec9 ("net/mlx5e: Implement queue mgmt ops and single channel swap") Signed-off-by: Bobby Eshleman Reviewed-by: Tariq Toukan Link: https://patch.msgid.link/20260803-mlx5-bql-v3-1-a30d4c66fe1d@meta.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 7d47a1da8b6b..f0407a850ea8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1939,8 +1939,10 @@ int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix, void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) { sq->txq = netdev_get_tx_queue(sq->netdev, sq->txq_ix); + /* Reset BQL only when the SQ has no bytes in flight. */ + if (sq->cc == sq->pc) + netdev_tx_reset_queue(sq->txq); set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - netdev_tx_reset_queue(sq->txq); netif_tx_start_queue(sq->txq); netif_queue_set_napi(sq->netdev, sq->txq_ix, NETDEV_QUEUE_TYPE_TX, sq->cq.napi); } From 1d0fc6c7ea49994b8ff50d02979d1e4207ec6c4f Mon Sep 17 00:00:00 2001 From: Shravya KN Date: Fri, 31 Jul 2026 12:09:33 -0700 Subject: [PATCH 068/116] bnxt_en: Move RSS table fill outside __bnxt_hwrm_vnic_set_rss() This is a refactor patch with no change in behavior. The caller will now fill the RSS table before calling __bnxt_hwrm_vnic_set_rss(). In the next patch, we'll add code to determine the default ring for the VNIC when we fill the RSS table. Reviewed-by: Kalesh AP Reviewed-by: Pavan Chebbi Signed-off-by: Shravya KN Signed-off-by: Michael Chan Link: https://patch.msgid.link/20260731190937.807270-2-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 004ef99f4530..4599b6e0d219 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6706,6 +6706,9 @@ static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) bool no_rss = !(vnic->flags & BNXT_VNIC_RSS_FLAG); u16 i, j; + if (!vnic->rss_table) + return; + /* Fill the RSS indirection table with ring group ids */ for (i = 0, j = 0; i < HW_HASH_INDEX_SIZE; i++) { if (!no_rss) @@ -6745,13 +6748,8 @@ static void __bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req, struct bnxt_vnic_info *vnic) { - if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - bnxt_fill_hw_rss_tbl_p5(bp, vnic); - if (bp->flags & BNXT_FLAG_CHIP_P7) - req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT; - } else { - bnxt_fill_hw_rss_tbl(bp, vnic); - } + if (bp->flags & BNXT_FLAG_CHIP_P7) + req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT; if (bp->rss_hash_delta) { req->hash_type = cpu_to_le32(bp->rss_hash_delta); @@ -6803,6 +6801,7 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, if (!set_rss) return hwrm_req_send(bp, req); + bnxt_fill_hw_rss_tbl_p5(bp, vnic); __bnxt_hwrm_vnic_set_rss(bp, req, vnic); ring_tbl_map = vnic->rss_table_dma_addr; nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings); @@ -10866,6 +10865,7 @@ static int __bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic) } skip_rss_ctx: + bnxt_fill_hw_rss_tbl(bp, vnic); /* configure default vnic, ring grp */ rc = bnxt_hwrm_vnic_cfg(bp, vnic); if (rc) { From 53f01cd594e223aabb538d5288e60111523c96f2 Mon Sep 17 00:00:00 2001 From: Shravya KN Date: Fri, 31 Jul 2026 12:09:34 -0700 Subject: [PATCH 069/116] bnxt_en: Determine and store default RX ring in vnic structure Each VNIC has a default RX ring. The purpose of the default RX ring is to provide a destination for any packets that cannot be parsed by the RSS logic. Up until now, the default RX ring is always Ring 0. We neglected to take care of this default RX ring when adding the queue restart feature. If ring 0 (default ring) is re-started, it may now have a new FW ring ID after freeing the old one and allocating a new one. The VNIC now may have a stale default ring and it may generate an internal exception. This exception may appear in dmesg: FW reported unknown error type 10 The best way to resolve this issue is to use a more appropriate ring for the default ring instead of always ring 0. Ring 0 may not even be in the RSS table, especially on a new RSS context. This patch adds the logic to determine and store the proper default RX ring for a VNIC. For an RSS VNIC, the default ring is the lowest ring number in the RSS table. The next patch will add proper logic to update the VNIC if the default ring changes after queue restart. Reviewed-by: Kalesh AP Reviewed-by: Pavan Chebbi Signed-off-by: Shravya KN Signed-off-by: Michael Chan Link: https://patch.msgid.link/20260731190937.807270-3-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 33 +++++++++++++++-------- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 + 2 files changed, 23 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4599b6e0d219..8b1f4e9fc780 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6704,25 +6704,36 @@ int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings) static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) { bool no_rss = !(vnic->flags & BNXT_VNIC_RSS_FLAG); - u16 i, j; + u16 i, j, min_j = bp->rx_nr_rings - 1; if (!vnic->rss_table) - return; + goto skip_rss_tbl; /* Fill the RSS indirection table with ring group ids */ for (i = 0, j = 0; i < HW_HASH_INDEX_SIZE; i++) { if (!no_rss) j = bp->rss_indir_tbl[i]; + min_j = min(j, min_j); vnic->rss_table[i] = cpu_to_le16(vnic->fw_grp_ids[j]); } + +skip_rss_tbl: + if (vnic->rss_table && !no_rss) + vnic->default_rx_ring = min_j; + else if (vnic->flags & BNXT_VNIC_RFS_FLAG) + vnic->default_rx_ring = vnic->vnic_id - 1; + else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp)) + vnic->default_rx_ring = bp->rx_nr_rings - 1; + else + vnic->default_rx_ring = 0; } static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic) { + u16 tbl_size, i, min_j = bp->rx_nr_rings - 1; __le16 *ring_tbl = vnic->rss_table; struct bnxt_rx_ring_info *rxr; - u16 tbl_size, i; tbl_size = bnxt_get_rxfh_indir_size(bp->dev); @@ -6735,6 +6746,7 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, j = ethtool_rxfh_context_indir(vnic->rss_ctx)[i]; else j = bp->rss_indir_tbl[i]; + min_j = min(j, min_j); rxr = &bp->rx_ring[j]; ring_id = rxr->rx_ring_struct.fw_ring_id; @@ -6742,6 +6754,7 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, ring_id = bnxt_cp_ring_for_rx(bp, rxr); *ring_tbl++ = cpu_to_le16(ring_id); } + vnic->default_rx_ring = min_j; } static void @@ -6938,8 +6951,9 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic) return rc; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0]; + struct bnxt_rx_ring_info *rxr; + rxr = &bp->rx_ring[vnic->default_rx_ring]; req->default_rx_ring_id = cpu_to_le16(rxr->rx_ring_struct.fw_ring_id); req->default_cmpl_ring_id = @@ -6972,13 +6986,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic) req->cos_rule = cpu_to_le16(0xffff); } - if (vnic->flags & BNXT_VNIC_RSS_FLAG) - ring = 0; - else if (vnic->flags & BNXT_VNIC_RFS_FLAG) - ring = vnic->vnic_id - 1; - else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp)) - ring = bp->rx_nr_rings - 1; - + ring = vnic->default_rx_ring; grp_idx = bp->rx_ring[ring].bnapi->index; req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id); req->lb_rule = cpu_to_le16(0xffff); @@ -11171,6 +11179,9 @@ static int bnxt_setup_nitroa0_vnic(struct bnxt *bp) return rc; } + /* Setup the proper default RX ring */ + bnxt_fill_hw_rss_tbl(bp, vnic); + rc = bnxt_hwrm_vnic_cfg(bp, vnic); if (rc) { netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n", diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 6335dfc14c98..44ea8fc7b766 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1334,6 +1334,7 @@ struct bnxt_vnic_info { #define BNXT_VNIC_RSSCTX_FLAG 0x40 struct ethtool_rxfh_context *rss_ctx; u32 vnic_id; + u16 default_rx_ring; }; struct bnxt_rss_ctx { From 0b137529a8997caf67190ca1d71ba8bbdb44fbfb Mon Sep 17 00:00:00 2001 From: Shravya KN Date: Fri, 31 Jul 2026 12:09:35 -0700 Subject: [PATCH 070/116] bnxt_en: Refresh VNIC default ring on queue restart if needed When a queue is restarted, refresh VNIC_CFG for all VNICs whose default RX ring is the restarted ring. This will eliminate this possible FW warning caused by a stale default ring in the VNIC: FW reported unknown error type 10 Fixes: 5ac066b7b062 ("bnxt_en: Fix queue start to update vnic RSS table") Reviewed-by: Kalesh AP Reviewed-by: Pavan Chebbi Signed-off-by: Shravya KN Signed-off-by: Michael Chan Link: https://patch.msgid.link/20260731190937.807270-4-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8b1f4e9fc780..6deb8f348d07 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11098,6 +11098,11 @@ static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic, vnic->vnic_id, rc); return rc; } + if (rxr_id == vnic->default_rx_ring) { + rc = bnxt_hwrm_vnic_cfg(bp, vnic); + if (rc) + return rc; + } } vnic->mru = mru; bnxt_hwrm_vnic_update(bp, vnic, From c3faf548a00f4c17100cc9204746975fa46a73b9 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 31 Jul 2026 12:09:36 -0700 Subject: [PATCH 071/116] bnxt_en: Disable EOP for TPA on all chips to prevent data corruption EOP (End of frame padding) on the AGG ring may cause overlapping of zero padding at the end of one segment with the next segment's data. If Relaxed Ordering (RO) is enabled, the zero padding may overwrite valid data in the next segment and corrupt the data. Older chips (P5 and older) do not automatically disable RO when EOP is enabled. On some ARM systems, data corruption was reported on 57508 (P5) chips with RO enabled. Always disable EOP on all chips on the AGG rings when TPA is enabled to fix the data corruption. Fixes: bfcd8d791ec1 ("bnxt_en: Add fast path logic for TPA on 57500 chips.") Reviewed-by: Pavan Chebbi Reviewed-by: Kalesh AP Signed-off-by: Michael Chan Link: https://patch.msgid.link/20260731190937.807270-5-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6deb8f348d07..25099077fe4f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4611,11 +4611,14 @@ static void bnxt_init_one_rx_agg_ring_rxbd(struct bnxt *bp, type = ((u32)rxr->rx_page_size << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_AGG_BD; - /* On P7, setting EOP will cause the chip to disable - * Relaxed Ordering (RO) for TPA data. Disable EOP for - * potentially higher performance with RO. + /* Disable EOP if TPA is enabled to prevent overlapping zero + * padding with the next segment's data. On P7_PLUS, EOP will + * automatically disable Relaxed Ordering (RO) to prevent + * potential data corruption (and may degrade performance). On + * older chips, RO will not be automatically disabled and may + * cause corruption. */ - if (BNXT_CHIP_P5_AND_MINUS(bp) || !(bp->flags & BNXT_FLAG_TPA)) + if (!(bp->flags & BNXT_FLAG_TPA)) type |= RX_BD_FLAGS_AGG_EOP; bnxt_init_rxbd_pages(ring, type); From 80eaf88efec33ac77ed7726d066c4f2f932cc329 Mon Sep 17 00:00:00 2001 From: Keegan Freyhof Date: Fri, 31 Jul 2026 12:09:37 -0700 Subject: [PATCH 072/116] bnxt_en: Fix PTP PPS setting bug The existing driver logic is always turning on PTP_CLK_REQ_PPS regardless of the "on" parameter passed to bnxt_ptp_enable(). During shutdown, PTP_CLK_REQ_PPS may be turned off and this bug will do the opposite and may trigger a PCIe PTM request TLP. On some systems this can trigger a PCIe AER. Fix it by properly configuring PTP_CLK_REQ_PPS based on the "on" parameter. Fixes: 9e518f25802c ("bnxt_en: 1PPS functions to configure TSIO pins") Reviewed-by: Pavan Chebbi Signed-off-by: Keegan Freyhof Signed-off-by: Michael Chan Link: https://patch.msgid.link/20260731190937.807270-6-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 5d41dc1bc782..b89293dfd2d1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -495,12 +495,15 @@ static int bnxt_ptp_enable(struct ptp_clock_info *ptp_info, return rc; case PTP_CLK_REQ_PPS: /* Configure PHC PPS IN */ - rc = bnxt_ptp_cfg_pin(bp, 0, BNXT_PPS_PIN_PPS_IN); + pin_id = 0; + if (!on) + break; + rc = bnxt_ptp_cfg_pin(bp, pin_id, BNXT_PPS_PIN_PPS_IN); if (rc) return rc; rc = bnxt_ptp_cfg_event(bp, BNXT_PPS_EVENT_INTERNAL); if (!rc) - ptp->pps_info.pins[0].event = BNXT_PPS_EVENT_INTERNAL; + ptp->pps_info.pins[pin_id].event = BNXT_PPS_EVENT_INTERNAL; return rc; default: netdev_err(ptp->bp->dev, "Unrecognized PIN function\n"); From aa2e13ae8d3cbe2c15ef4f7e971b2de0832794aa Mon Sep 17 00:00:00 2001 From: Qing Luo Date: Tue, 4 Aug 2026 10:55:14 +0800 Subject: [PATCH 073/116] sctp: fix addip_serial increment on ASCONF_ACK allocation failure In sctp_process_asconf(), when sctp_make_asconf_ack() fails to allocate the ASCONF_ACK chunk due to memory pressure, the code jumps to the done label where asoc->peer.addip_serial is unconditionally incremented. This leaves the peer's ASCONF (serial N) unacknowledged while the local endpoint now expects serial N+1. When the peer retransmits serial N, it falls into the serial < addip_serial + 1 branch , which attempts to look up a cached ACK for serial N. No cached ACK exists since the allocation failed, so the retransmission is silently discarded. The peer eventually times out and ABORTs the association. Move the addip_serial increment inside the if (asconf_ack) block so that the serial number is only advanced when the ASCONF_ACK is successfully created and cached. This way, on allocation failure, the serial number is unchanged and the peer's retransmitted ASCONF will be correctly re-processed. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Qing Luo Acked-by: Xin Long Link: https://patch.msgid.link/20260804025514.241767-1-l1138897701@163.com Signed-off-by: Jakub Kicinski --- net/sctp/sm_make_chunk.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 0ae30c3c8913..e25612e9d082 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3336,12 +3336,11 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, goto done; } done: - asoc->peer.addip_serial++; - /* If we are sending a new ASCONF_ACK hold a reference to it in assoc * after freeing the reference to old asconf ack if any. */ if (asconf_ack) { + asoc->peer.addip_serial++; sctp_chunk_hold(asconf_ack); list_add_tail(&asconf_ack->transmitted_list, &asoc->asconf_ack_list); From a0ab2ba83e35159d81cec830a92e885ecf8139be Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Mon, 3 Aug 2026 14:17:38 +0800 Subject: [PATCH 074/116] tcp: fix TFO max_qlen accounting across reuseport migration A listener's TCP_FASTOPEN max_qlen stops being accurate and lets through far more pending Fast Open requests than it was configured for. This only shows up with SO_REUSEPORT listener migration, where closing a listener hands its still-pending TFO children over to a surviving one. fastopenq.qlen is charged in tcp_fastopen_create_child() when the child is created and uncharged in reqsk_fastopen_remove() when the handshake completes. The uncharge follows rsk_listener of the request the child points at, and inet_reqsk_clone() has repointed the child at a new request owned by the new listener, so the ++ and the -- land on two different sockets. The new listener's qlen drifts negative and its limit no longer binds. Charge the new listener during migration, like reqsk_queue_migrated() already does for queue->young and queue->qlen. Fixes: 54b92e841937 ("tcp: Migrate TCP_ESTABLISHED/TCP_SYN_RECV sockets in accept queues.") Signed-off-by: Jiayuan Chen Reviewed-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260803061739.134737-1-jiayuan.chen@linux.dev Signed-off-by: Jakub Kicinski --- net/ipv4/inet_connection_sock.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 56902bba5483..6257459bcee2 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -943,11 +943,23 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, nreq->rsk_listener = sk; - /* We need not acquire fastopenq->lock - * because the child socket is locked in inet_csk_listen_stop(). - */ - if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) { + struct fastopen_queue *fastopenq; + + /* reqsk_fastopen_remove() will uncharge nreq->rsk_listener, + * that is @sk, so charge it here. Unlike the listener + * being closed, @sk is live and needs its lock. + */ + fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; + spin_lock_bh(&fastopenq->lock); + fastopenq->qlen++; + spin_unlock_bh(&fastopenq->lock); + + /* We need not acquire fastopenq->lock + * because the child socket is locked in inet_csk_listen_stop(). + */ rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); + } return nreq; } From 8aecf0bbcc72605592134c917c222207d8f63ab0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 4 Aug 2026 09:33:28 +0000 Subject: [PATCH 075/116] netfilter: nf_flow_table: drop existing skb dst before skb_dst_set_noref() Incoming skbs passing through netfilter flowtable offload hooks (or XFRM offload path) might already carry a ref-counted dst_entry assigned during earlier RX or routing steps. Calling skb_dst_set_noref() when skb already holds a ref-counted dst overwrites skb->_skb_refdst, leaking the previous dst_entry reference count and triggering a DEBUG_NET_WARN_ON_ONCE assertion in skb_dst_check_unset(): WARNING: at skb_dst_check_unset include/linux/skbuff.h:1170 WARNING: at skb_dst_set_noref include/linux/skbuff.h:1234 WARNING: at nf_flow_offload_ip_hook+0xf6c/0x2b60 net/netfilter/nf_flow_table_ip.c:864 Drop any existing dst_entry reference with skb_dst_drop(skb) before setting the non-referenced flowtable destination. Fixes: 2a79fd3908ac ("netfilter: nf_flow_table: attach dst to skbs") Reported-by: syzbot+76d4e3a055aec3b007ec@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a71b141.9511d2ce.1fc5b9.033b.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Reviewed-by: Pablo Neira Ayuso Link: https://patch.msgid.link/20260804093328.1831847-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/netfilter/nf_flow_table_ip.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 0b78decce8a9..c9e332fafcb5 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -310,6 +310,7 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, struct dst_entry *dst) { skb_orphan(skb); + skb_dst_drop(skb); skb_dst_set_noref(skb, dst); dst_output(state->net, state->sk, skb); return NF_STOLEN; @@ -861,6 +862,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, return NF_DROP; } xmit.dest = neigh->ha; + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); break; case FLOW_OFFLOAD_XMIT_DIRECT: @@ -1178,6 +1180,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, return NF_DROP; } xmit.dest = neigh->ha; + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); break; case FLOW_OFFLOAD_XMIT_DIRECT: From 5f26a690e8efa54315e4922368daf54e0b8f5515 Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Sun, 2 Aug 2026 09:23:34 +0000 Subject: [PATCH 076/116] mac802154: fix netdev use-after-free in beacon worker mac802154_beacon_worker() reads local->beacon_req under RCU and derives the sub-interface from the request, but then drops the RCU read lock and continues to use both sdata and the embedded wpan_dev. mac802154_stop_beacons_locked() cancels only pending beacon work, clears local->beacon_req and frees the request. A beacon worker that is already running can therefore continue after interface teardown and dereference the freed netdev private area. The scan worker already pins the netdev before leaving RCU. Apply the same lifetime rule to the beacon worker: take a netdev reference while the request is still protected by RCU, and release it on all paths that continue after the reference is acquired. Fixes: 3accf4762734 ("mac802154: Handle basic beaconing") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zihan Xi Reviewed-by: Miquel Raynal Link: https://patch.msgid.link/e9a3909c7a6281967961773ca841e860b8ecf40e.1785596603.git.zihanx@nebusec.ai Signed-off-by: Jakub Kicinski --- net/mac802154/scan.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 65089826ff59..005338f89b75 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -415,6 +415,7 @@ void mac802154_beacon_worker(struct work_struct *work) container_of(work, struct ieee802154_local, beacon_work.work); struct cfg802154_beacon_request *beacon_req; struct ieee802154_sub_if_data *sdata; + netdevice_tracker dev_tracker; struct wpan_dev *wpan_dev; u8 interval; int ret; @@ -427,12 +428,14 @@ void mac802154_beacon_worker(struct work_struct *work) } sdata = IEEE802154_WPAN_DEV_TO_SUB_IF(beacon_req->wpan_dev); + netdev_hold(sdata->dev, &dev_tracker, GFP_ATOMIC); /* Wait an arbitrary amount of time in case we cannot use the device */ if (local->suspended || !ieee802154_sdata_running(sdata)) { rcu_read_unlock(); queue_delayed_work(local->mac_wq, &local->beacon_work, msecs_to_jiffies(1000)); + netdev_put(sdata->dev, &dev_tracker); return; } @@ -450,6 +453,7 @@ void mac802154_beacon_worker(struct work_struct *work) if (interval < IEEE802154_ACTIVE_SCAN_DURATION) queue_delayed_work(local->mac_wq, &local->beacon_work, local->beacon_interval); + netdev_put(sdata->dev, &dev_tracker); } int mac802154_stop_beacons_locked(struct ieee802154_local *local, From afa58b7384913c8773d837acdb07b035690ec5d2 Mon Sep 17 00:00:00 2001 From: Henry Martin Date: Mon, 3 Aug 2026 12:36:18 +0800 Subject: [PATCH 077/116] net/ncsi: fix heap OOB read in NCSI_CMD_SEND_CMD payload length ncsi_send_cmd_nl() takes the number of bytes to copy from the attacker-controlled ncsi_pkt_hdr.length field of the in-band packet header, while the source buffer is the NCSI_ATTR_DATA netlink attribute whose readable size is nla_len() - sizeof(ncsi_pkt_hdr). The two length sources are never cross-checked: only nla_len() >= sizeof(struct ncsi_pkt_hdr) is enforced. With hdr->length set larger than the attribute payload (up to 65535 against at most 2032 readable bytes), ncsi_cmd_handler_oem() copies past the end of the netlink attribute buffer with unsafe_memcpy(), leaking up to ~64KB of kernel heap memory into the transmitted NCSI command packet. The destination skb is sized by the declared payload, so the write side does not overflow - this is a pure OOB read / information leak, reachable with CAP_NET_ADMIN on systems with a registered NCSI device (e.g. OpenBMC on Aspeed BMC SoCs, where NET_NCSI=y is standard). Reject commands whose declared payload extends past the end of the data attribute. The issue was found by the autokbug dynamic kernel fuzzer at Tencent Yunding Lab. Fixes: 9771b8ccdfa6 ("net/ncsi: Extend NC-SI Netlink interface to allow user space to send NC-SI command") Reported-by: Henry Martin Signed-off-by: Henry Martin Link: https://patch.msgid.link/20260803043618.3210301-1-bsdhenrymartin@gmail.com Signed-off-by: Jakub Kicinski --- net/ncsi/ncsi-netlink.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 2f872d064396..8cc538358f6a 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -461,6 +461,10 @@ static int ncsi_send_cmd_nl(struct sk_buff *msg, struct genl_info *info) nca.req_flags = NCSI_REQ_FLAG_NETLINK_DRIVEN; nca.info = info; nca.payload = ntohs(hdr->length); + if (nca.payload > len - sizeof(*hdr)) { + ret = -EINVAL; + goto out_netlink; + } nca.data = data + sizeof(*hdr); ret = ncsi_xmit_cmd(&nca); From f803c086399da277b5d0ff36a107d0f162751800 Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Mon, 3 Aug 2026 14:12:33 +0800 Subject: [PATCH 078/116] ip6_tunnel: clear skb2->cb[] in ip6ip6_err() ip6ip6_err() clones an outer IPv6 ICMP error skb, pulls it to the quoted inner IPv6 packet, and then passes the clone to icmpv6_send(). The clone still carries the outer packet's inet6_skb_parm in skb->cb. If the outer packet had a Home Address Option, IP6CB(skb2)->dsthao remains non-zero after skb_pull(). icmpv6_send() later calls mip6_addr_swap(), which uses that stale dsthao offset against the quoted inner packet. A malformed inner destination-options header can then make the HAO lookup and address swap run past the end of the quoted packet and corrupt skb_shared_info. Clear skb2->cb[] before pulling the quoted inner IPv6 packet so the reply path does not reuse metadata left by the outer IPv6 stack. Fixes: e490d1d85cf5 ("[IPV6] IP6TUNNEL: Split out generic routine in ip6ip6_err().") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zhiling Zou Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/fe1a5e765fbca88d69391887f0ed26a19e3e4d39.1785736562.git.zhilinz@nebusec.ai Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_tunnel.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index bf8e40af60b0..ebf83f090376 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -684,6 +684,9 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!skb2) return 0; + /* Remove debris left by outer IPv6 stack. */ + memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2))); + skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); From 3874892dd27d5387aa9a06f58d9060f18f351d24 Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Sun, 2 Aug 2026 15:46:12 -0700 Subject: [PATCH 079/116] net: tap: set skb->dev before parsing virtio net header in tap_get_user_xdp() The commit 4f61f133f354 ("net: tap: NULL pointer derefence in dev_parse_header_protocol when skb->dev is null") fixed a crash in tap_get_user() by assigning skb->dev before calling tun_vnet_hdr_to_skb(). This is required because virtio_net_hdr_to_skb() may invoke dev_parse_header_protocol(), which dereferences skb->dev. Without the assignment, a NULL pointer dereference can occur. However, tap_get_user_xdp() still parses the virtio-net header before assigning skb->dev. When the vhost TX path passes an XDP buffer containing a GSO virtio-net header but the protocol is set to zero on purpose, tun_vnet_hdr_to_skb() can reach dev_parse_header_protocol() while skb->dev is still NULL, resulting in a crash. Fix this by looking up the tap device and assigning skb->dev before calling tun_vnet_hdr_to_skb(), matching the ordering already used in tap_get_user(). Preserve the existing RCU read-side critical section across dev_queue_xmit(). Fixes: 924a9bc362a5 ("net: check if protocol extracted by virtio_net_hdr_set_proto is correct") Cc: stable@vger.kernel.org Signed-off-by: Dongli Zhang Reviewed-by: Willem de Bruijn Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20260802224612.264563-1-dongli.zhang@oracle.com Signed-off-by: Jakub Kicinski --- drivers/net/tap.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index fae115915c8e..5d2d34d24ce8 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1074,10 +1074,21 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) skb_reset_mac_header(skb); skb->protocol = eth_hdr(skb)->h_proto; + rcu_read_lock(); + tap = rcu_dereference(q->tap); + if (!tap) { + kfree_skb(skb); + rcu_read_unlock(); + return 0; + } + skb->dev = tap->dev; + if (vnet_hdr_len) { err = tun_vnet_hdr_to_skb(q->flags, skb, gso); - if (err) + if (err) { + rcu_read_unlock(); goto err_kfree; + } } /* Move network header to the right position for VLAN tagged packets */ @@ -1085,15 +1096,8 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); - rcu_read_lock(); - tap = rcu_dereference(q->tap); - if (tap) { - skb->dev = tap->dev; - skb_probe_transport_header(skb); - dev_queue_xmit(skb); - } else { - kfree_skb(skb); - } + skb_probe_transport_header(skb); + dev_queue_xmit(skb); rcu_read_unlock(); return 0; From 8ae344eb540af3f457179b52bc6061416752485c Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Fri, 31 Jul 2026 22:19:06 +0800 Subject: [PATCH 080/116] net: prestera: validate firmware header length prestera_fw_hdr_parse() reads the firmware header before checking that the firmware image contains that header. Reject images shorter than struct prestera_fw_header before decoding the magic and version fields. Fixes: 4c2703dfd7fabb ("net: marvell: prestera: Add PCI interface support") Signed-off-by: Pengpeng Hou Acked-by: Elad Nachman Link: https://patch.msgid.link/20260731141500.1-prestera-v2-pengpeng@iscas.ac.cn Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/prestera/prestera_pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 2989a77e3b42..1ad0e62a8433 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -684,6 +684,9 @@ static int prestera_fw_hdr_parse(struct prestera_fw *fw) struct prestera_fw_header *hdr; u32 magic; + if (fw->bin->size < sizeof(*hdr)) + return -EINVAL; + hdr = (struct prestera_fw_header *)fw->bin->data; magic = be32_to_cpu(hdr->magic_number); From c27e360545373b7aee9862a5beef3b9fb3df0c25 Mon Sep 17 00:00:00 2001 From: Hidayath Khan Date: Thu, 30 Jul 2026 14:42:27 +0200 Subject: [PATCH 081/116] dibs: initialise dibs->lock in dibs_dev_alloc() dibs->lock is initialised by dibs_dev_add(), but a dibs device can already take interrupts before that call: ism_probe() runs ism_dev_init(), and hence request_irq(), before it calls dibs_dev_add(). No client can have registered a dmb at that point, so no dmb interrupt can occur, but a GID event interrupt can, and ism_handle_irq() takes dibs->lock unconditionally on entry, before it inspects anything else. Initialise the lock in dibs_dev_alloc() instead, so that it is valid as soon as a driver can publish the device to its interrupt handler. Fixes: cc21191b584c ("dibs: Move data path to dibs layer") Cc: stable@vger.kernel.org Reviewed-by: Alexandra Winter Signed-off-by: Hidayath Khan Link: https://patch.msgid.link/20260730124227.167829-1-hidayath@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/dibs/dibs_main.c | 2 +- include/linux/dibs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dibs/dibs_main.c b/drivers/dibs/dibs_main.c index 14c3e2d84902..4c26fd06973f 100644 --- a/drivers/dibs/dibs_main.c +++ b/drivers/dibs/dibs_main.c @@ -138,6 +138,7 @@ struct dibs_dev *dibs_dev_alloc(void) dibs = kzalloc_obj(*dibs); if (!dibs) return dibs; + spin_lock_init(&dibs->lock); dibs->dev.release = dibs_dev_release; dibs->dev.class = &dibs_class; device_initialize(&dibs->dev); @@ -186,7 +187,6 @@ int dibs_dev_add(struct dibs_dev *dibs) int i, ret; max_dmbs = dibs->ops->max_dmbs(); - spin_lock_init(&dibs->lock); dibs->dmb_clientid_arr = kzalloc(max_dmbs, GFP_KERNEL); if (!dibs->dmb_clientid_arr) return -ENOMEM; diff --git a/include/linux/dibs.h b/include/linux/dibs.h index c75607f8a5cf..d3e0777f25ae 100644 --- a/include/linux/dibs.h +++ b/include/linux/dibs.h @@ -439,7 +439,7 @@ static inline void *dibs_get_priv(struct dibs_dev *dev, /** * dibs_dev_alloc() - allocate and reference device structure * - * The following fields will be valid upon successful return: dev + * The following fields will be valid upon successful return: dev, lock * NOTE: Use put_device(dibs_get_dev(@dibs)) to give up your reference instead * of freeing @dibs @dev directly once you have successfully called this * function. From 44871eadd07a7f004aa00cb87399461eea08c630 Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Tue, 4 Aug 2026 21:05:54 +0800 Subject: [PATCH 082/116] MAINTAINERS: add myself as a maintainer for Hisilicon Network Subsystem I am already listed as a maintainer for the HNS3 and HIBMCGE drivers, but not for the broader Hisilicon Network Subsystem entry, whose file pattern covers drivers/net/ethernet/hisilicon/ (e.g. the legacy hns driver). As a result, patches to those files are not CC'd to me. Add myself alongside Jian Shen to help maintain these legacy Hisilicon ethernet drivers and ensure patches in this tree are routed to me. Signed-off-by: Jijie Shao Acked-by: Jian Shen Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260804130554.871716-1-shaojijie@huawei.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 0d7987278c07..a77cf599bac2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11743,6 +11743,7 @@ F: drivers/net/ethernet/hisilicon/hibmcge/ HISILICON NETWORK SUBSYSTEM DRIVER M: Jian Shen +M: Jijie Shao L: netdev@vger.kernel.org S: Maintained W: http://www.hisilicon.com From b8a39a09ae4eaae04309e1e38ed6a1101d967496 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 4 Aug 2026 15:20:48 +0000 Subject: [PATCH 083/116] net: remove WARN_ON_ONCE() from sk_mc_loop() sk_mc_loop() can be called for sockets that are neither AF_INET nor AF_INET6 (e.g. AF_PACKET sockets when sending packets via raw/packet socket over virtual devices such as VRF or ipvlan). In such cases, sk_family is not AF_INET/AF_INET6 and sk_mc_loop() falls through the switch statement and triggers WARN_ON_ONCE(1). Non-INET sockets do not support IP_MULTICAST_LOOP or IPV6_MULTICAST_LOOP options, so loopback should default to true without generating a warning. Fixes: f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack") Reported-by: syzbot+22c3218a6fa219e47321@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a72024c.13623e66.bdc14.0019.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260804152048.2134341-1-edumazet@google.com Signed-off-by: Paolo Abeni --- net/core/sock.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index ffa73594c13c..1ad41904db25 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -779,7 +779,6 @@ bool sk_mc_loop(const struct sock *sk) return inet6_test_bit(MC6_LOOP, sk); #endif } - WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); From 185a4caeecabc150106deda1da170b09f2ad803f Mon Sep 17 00:00:00 2001 From: Sidraya Jayagond Date: Mon, 3 Aug 2026 09:07:01 +0200 Subject: [PATCH 084/116] net/smc: fix TOCTOU race between smc_listen_out() and listener close smc_listen_out() reads lsmc->sk.sk_state without the listener lock, then acquires lock_sock_nested() only after the check passes. This opens a window where smc_close_active() can transition the listener to SMC_CLOSED, call smc_close_cleanup_listen() to drain the accept queue, and release the lock, all between the lockless read and the delayed lock acquisition: smc_listen_work (smc_hs_wq) smc_close_active() ------------------------------- ------------------------- release_sock(child) if (sk_state == SMC_LISTEN) TRUE lock_sock(listener) sk_state = SMC_CLOSED smc_close_cleanup_listen() release_sock(listener) flush_work(tcp_listen_work) lock_sock_nested(listener) smc_accept_enqueue(listener, child) /* child enqueued on dead listener */ smc_close_active() flushes only tcp_listen_work. Work items already dispatched onto smc_hs_wq for the CLC handshake continue running unguarded. smc_accept_enqueue() takes a sock_hold() on the child that is never released, so the child smc_sock, its clcsock, and the reference all leak. A remote peer that opens TCP connections while the server calls close() can exhaust kernel memory. Move lock_sock_nested() to before the sk_state check so that the test and the enqueue are atomic under the listener lock. Fixes: fd57770dd198 ("net/smc: wait for pending work before clcsock release_sock") Reviewed-by: Mahanta Jambigi Signed-off-by: Sidraya Jayagond Reviewed-by: Breno Leitao Reviewed-by: Dust Li Link: https://patch.msgid.link/20260803070701.126339-1-sidraya@linux.ibm.com Signed-off-by: Paolo Abeni --- net/smc/af_smc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b5db69073e20..00403175b740 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1931,11 +1931,12 @@ static void smc_listen_out(struct smc_sock *new_smc) atomic_dec(&lsmc->queued_smc_hs); release_sock(newsmcsk); /* lock in smc_listen_work() */ + lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); if (lsmc->sk.sk_state == SMC_LISTEN) { - lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); release_sock(&lsmc->sk); } else { /* no longer listening */ + release_sock(&lsmc->sk); smc_close_non_accepted(newsmcsk); } From f684c514f7965385dae21f2535f99938e73ec1af Mon Sep 17 00:00:00 2001 From: Ahmed Naseef Date: Tue, 4 Aug 2026 15:35:11 +0400 Subject: [PATCH 085/116] net: phy: mediatek: fix TX blink masks using the RX bits MTK_GPHY_LED_TX_BLINK_SET and MTK_2P5GPHY_LED_TX_BLINK_SET are built from the RX blink bits instead of the TX ones, so both TX masks are identical to their RX counterparts. The TX bits they should be using, MTK_PHY_LED_BLINK_{10,100,1000,2500}TX, are otherwise only referenced by the per-speed branch of mtk_phy_led_hw_ctrl_set(). A TX trigger selected without a link trigger therefore programs the RX blink bits, and the LED blinks on received traffic. The masks are also used to decode the blink register in mtk_phy_led_hw_ctrl_get(), which as a result cannot tell the two triggers apart: an RX-only configuration reads back as RX and TX, and a TX-only configuration reads back as neither. Fixes: 7f9c320c98db ("net: phy: mediatek: Move LED helper functions into mtk phy lib") Cc: stable@vger.kernel.org Signed-off-by: Ahmed Naseef Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260804113511.3371248-1-naseefkm@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/phy/mediatek/mtk.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h index 320f76ffa81f..79e09727b81b 100644 --- a/drivers/net/phy/mediatek/mtk.h +++ b/drivers/net/phy/mediatek/mtk.h @@ -53,15 +53,15 @@ #define MTK_GPHY_LED_RX_BLINK_SET (MTK_PHY_LED_BLINK_1000RX | \ MTK_PHY_LED_BLINK_100RX | \ MTK_PHY_LED_BLINK_10RX) -#define MTK_GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_1000RX | \ - MTK_PHY_LED_BLINK_100RX | \ - MTK_PHY_LED_BLINK_10RX) +#define MTK_GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_1000TX | \ + MTK_PHY_LED_BLINK_100TX | \ + MTK_PHY_LED_BLINK_10TX) #define MTK_2P5GPHY_LED_ON_SET (MTK_PHY_LED_ON_LINK2500 | \ MTK_GPHY_LED_ON_SET) #define MTK_2P5GPHY_LED_RX_BLINK_SET (MTK_PHY_LED_BLINK_2500RX | \ MTK_GPHY_LED_RX_BLINK_SET) -#define MTK_2P5GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_2500RX | \ +#define MTK_2P5GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_2500TX | \ MTK_GPHY_LED_TX_BLINK_SET) #define MTK_PHY_LED_STATE_FORCE_ON 0 From 7e2d693af0d4c05bddccb3541a0aabd69f4cb244 Mon Sep 17 00:00:00 2001 From: "Sergey V. Frolov" Date: Tue, 4 Aug 2026 15:04:48 +0300 Subject: [PATCH 086/116] net: octeontx2-pf: Fix UB in shift operation In function otx2_get_egress_burst_cfg, when the parameter `burst` is 255 and the max mantissa is 255 (0xFFULL), `burst_exp` is set to `ilog2(255) - 1`, which equals 6. This results in an unsigned wrap-around when calculating `(1ULL << (*burst_exp - 7))`, since `*burst_exp - 7` becomes -1, which makes the shift operand 0xFFFFFFFF. This value is greater than the width of the left operand. According to standard 6.5.7 p.3: "The type of the result is that of the promoted left operand. If the value of the right operand is negative or is greater than or equal to the width of the promoted left operand, the behavior is undefined." Fix the off-by-one boundary condition. Add a WARN_ON(*burst_exp < 7) before the else branch as an explicit safeguard. This ensures that if max_mantissa ever changes in a way that reintroduces this condition, it will be immediately caught at runtime rather than silently triggering UB. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: e638a83f167e ("octeontx2-pf: TC_MATCHALL egress ratelimiting offload") Signed-off-by: Sergey V. Frolov Cc: stable@vger.kernel.org Reviewed-by: Ratheesh Kannoth Reviewed-by: Sunil Goutham Link: https://patch.msgid.link/20260804120446.1955448-1-Sergey.V.Frolov@kaspersky.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 0b46ec29e64e..039fd47ebf52 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -54,10 +54,12 @@ static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst, if (burst) { *burst_exp = ilog2(burst) ? ilog2(burst) - 1 : 0; tmp = burst - rounddown_pow_of_two(burst); - if (burst < max_mantissa) + if (burst <= max_mantissa) { *burst_mantissa = tmp * 2; - else + } else { + WARN_ON(*burst_exp < 7); *burst_mantissa = tmp / (1ULL << (*burst_exp - 7)); + } } else { *burst_exp = MAX_BURST_EXPONENT; *burst_mantissa = max_mantissa; From dedd34b0f2310e28c5f6d4875cfbf4b7ed821c01 Mon Sep 17 00:00:00 2001 From: Zijie Huang Date: Sat, 1 Aug 2026 21:42:33 +0800 Subject: [PATCH 087/116] net/sched: reject overly deep qdisc hierarchies Deep qdisc hierarchies can lead to excessive recursion in qdisc tree walkers and exhaust the kernel stack. The existing loop check does not cover the create-and-graft path, so a hierarchy can still be extended by creating a new child qdisc below an already deep parent. Store the hierarchy depth in struct Qdisc and update it when qdiscs are grafted. Reject new child qdiscs once the parent is already at the maximum allowed depth. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Suggested-by: Jamal Hadi Salim Reported-by: Vega Assisted-by: Codex:gpt-5.4 Signed-off-by: Zijie Huang Signed-off-by: Ren Wei Reviewed-by: Victor Nogueira Link: https://patch.msgid.link/1e9ab39597423fd5d13cfaaf52279b8ee3d9fc3c.1785434373.git.milkory@outlook.com Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- include/net/sch_generic.h | 1 + net/sched/sch_api.c | 9 +++++++++ 2 files changed, 10 insertions(+) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 45a1e8c78222..cbc248776511 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -99,6 +99,7 @@ struct Qdisc { struct hlist_node hash; u32 handle; u32 parent; + int depth; struct netdev_queue *dev_queue; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 668bcd60d183..65b35528d125 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1114,6 +1114,9 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, unsigned int i, num_q, ingress; struct netdev_queue *dev_queue; + if (new) + new->depth = 0; + ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || @@ -1211,9 +1214,15 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, NL_SET_ERR_MSG(extack, "STAB not supported on a non root"); return -EINVAL; } + if (new && parent->depth >= 7) { + NL_SET_ERR_MSG(extack, "Qdisc hierarchy is too deep"); + return -E2BIG; + } err = cops->graft(parent, cl, new, &old, extack); if (err) return err; + if (new) + new->depth = parent->depth + 1; notify_and_destroy(net, skb, n, classid, old, new, extack); } return 0; From d8eb9a06b922418598eac38fb9772ea4e9ef4273 Mon Sep 17 00:00:00 2001 From: Zijie Huang Date: Sat, 1 Aug 2026 21:42:34 +0800 Subject: [PATCH 088/116] selftests/tc-testing: add qdisc hierarchy depth tests Add tdc coverage for the qdisc hierarchy depth limit. The tests verify that the deepest allowed hierarchy can still be created and that adding another child qdisc below it is rejected. Signed-off-by: Zijie Huang Assisted-by: Codex:gpt-5.4 Signed-off-by: Ren Wei Reviewed-by: Victor Nogueira Link: https://patch.msgid.link/5cc2d26a7c8e553759cdd29a3116f843fabc25ba.1785434373.git.milkory@outlook.com Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- .../tc-testing/tc-tests/qdiscs/depth.json | 74 +++++++++++++++++++ 1 file changed, 74 insertions(+) create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/depth.json diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/depth.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/depth.json new file mode 100644 index 000000000000..48f8683f0d1a --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/depth.json @@ -0,0 +1,74 @@ +[ + { + "id": "ad43", + "name": "Create qdisc hierarchy at maximum depth", + "category": [ + "qdisc", + "depth" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: htb default 1", + "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: htb default 1", + "$TC class add dev $DUMMY parent 2: classid 2:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 2:1 handle 3: htb default 1", + "$TC class add dev $DUMMY parent 3: classid 3:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 3:1 handle 4: htb default 1", + "$TC class add dev $DUMMY parent 4: classid 4:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 4:1 handle 5: htb default 1", + "$TC class add dev $DUMMY parent 5: classid 5:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 5:1 handle 6: htb default 1", + "$TC class add dev $DUMMY parent 6: classid 6:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 6:1 handle 7: htb default 1", + "$TC class add dev $DUMMY parent 7: classid 7:1 htb rate 10mbit" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 7:1 handle 8: htb default 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc htb 8: parent 7:1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + }, + { + "id": "c519", + "name": "Reject qdisc hierarchy above maximum depth", + "category": [ + "qdisc", + "depth" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: htb default 1", + "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: htb default 1", + "$TC class add dev $DUMMY parent 2: classid 2:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 2:1 handle 3: htb default 1", + "$TC class add dev $DUMMY parent 3: classid 3:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 3:1 handle 4: htb default 1", + "$TC class add dev $DUMMY parent 4: classid 4:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 4:1 handle 5: htb default 1", + "$TC class add dev $DUMMY parent 5: classid 5:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 5:1 handle 6: htb default 1", + "$TC class add dev $DUMMY parent 6: classid 6:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 6:1 handle 7: htb default 1", + "$TC class add dev $DUMMY parent 7: classid 7:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 7:1 handle 8: htb default 1", + "$TC class add dev $DUMMY parent 8: classid 8:1 htb rate 10mbit" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 8:1 handle 9: htb default 1", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc htb 9:", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + } +] From 7fc1c937b6b37c77df4ba374c37435ab06a2e945 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C5=81ukasz=20Patron?= Date: Tue, 4 Aug 2026 22:18:30 +0200 Subject: [PATCH 089/116] net: qrtr: ns: Raise lookup limit to 128 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Current limit of 64 is not enough for Sony Xperia 10 VII (SM6475). After merging v6.6.142 into a downstream AOSP device, it's stuck on boot animation and following log spam can be observed in dmesg: E qrtr : ctrl_cmd_new_lookup(): QRTR client node exceeds max lookup limit! E qrtr : qrtr_ns_worker(): failed while handling packet from 1:16600 No idea why it needs more than 64 client lookups, but it appears to work fine with 128 as it did when there were no limits. I don't really have a good way to investigate what it needs all these lookups for as most of the userspace is closed source. Fixes: 5640227d9a21 ("net: qrtr: ns: Limit the maximum number of lookups") Signed-off-by: Łukasz Patron Link: https://patch.msgid.link/20260804201919.1148015-1-priv.luk@gmail.com Signed-off-by: Jakub Kicinski --- net/qrtr/ns.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index e5b2adb161d9..c5e7e01db249 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -78,7 +78,7 @@ struct qrtr_node { */ #define QRTR_NS_MAX_NODES 512 #define QRTR_NS_MAX_SERVERS 256 -#define QRTR_NS_MAX_LOOKUPS 64 +#define QRTR_NS_MAX_LOOKUPS 128 static u16 node_count; From 68bf02b6b4ad3f748c6db71fd77b6c0402d252f4 Mon Sep 17 00:00:00 2001 From: Fan XinRan Date: Mon, 3 Aug 2026 14:38:50 +0000 Subject: [PATCH 090/116] net: thunderbolt: Tear down DMA paths before stopping the rings tbnet_tear_down() stops both rings and frees their frame buffers before calling tb_xdomain_disable_paths(). tb_ring_stop() zeroes the ring's descriptor base and tbnet_free_buffers() unmaps and frees the pages the frames sit in, so by the time __tb_path_deactivate_hop() polls the hop's 'pending' bit, anything still in flight has nowhere to drain to. The teardown sequence has been in this order since the driver was added. The setup path has not: commit ff7cd07f3064 ("net: thunderbolt: Enable DMA paths only after rings are enabled") moved the path enable to the end of tbnet_connected_work() and documented why: /* Both logins successful so enable the rings, high-speed DMA * paths and start the network device queue. * * Note we enable the DMA paths last to make sure we have primed * the Rx ring before any incoming packets are allowed to * arrive. */ Teardown was never updated to match, so the rings and the paths now come down in the same order they go up instead of in reverse. On an ASMedia ASM4242 host router the 'pending' bit then never clears: every teardown burns the full 500 ms timeout and __tb_path_deactivate_hop() returns -ETIMEDOUT. Raising the timeout to 5 s does not help, so the hop is not slow to drain, it never drains at all. The failure is invisible above the thunderbolt core. __tb_path_deactivate_hops() is void and only calls tb_port_warn(); tb_path_deactivate(), tb_tunnel_deactivate() and __tb_disconnect_xdomain_paths() are void as well, and tb_disconnect_xdomain_paths() ends in an unconditional "return 0". So tb_xdomain_disable_paths() reports success and the netdev_warn() below it never fires. Repeated teardowns eventually take the XDomain control channel down, after which the peer node is gone and only a power cycle brings the controller back. Deactivating the paths first fixes it. Measured with kretprobes on a stock v6.17 tree with no other patches applied, on a link that was up and had just carried traffic: before: __tb_path_deactivate_hop() returns 0 for the first hop, then -ETIMEDOUT for the second 500335 us later after: 0 for both, 525 us apart Alternating the two orderings ABBA over three load levels, four teardowns per arm: every teardown failed before the change (21 of 21 that ran), none failed after (0 of 24). The before arms ran short because the link died partway through. The same split shows up when the interface is enslaved to a bond instead of just brought down, which is how I ran into this in the first place. Throughput and latency after the change are unchanged. Hosts whose routers drain the hop despite the stale descriptor base see no functional difference, since the paths end up deactivated either way. Fixes: e69b6c02b4c3 ("net: Add support for networking over Thunderbolt cable") Signed-off-by: Fan XinRan Acked-by: Mika Westerberg Link: https://patch.msgid.link/20260803-b4-tbnet-teardown-v2-1-27de6a13ca2d@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/thunderbolt/main.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/thunderbolt/main.c b/drivers/net/thunderbolt/main.c index c5670d61820c..98893732bc6e 100644 --- a/drivers/net/thunderbolt/main.c +++ b/drivers/net/thunderbolt/main.c @@ -386,11 +386,16 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout) break; } - tb_ring_stop(net->rx_ring.ring); - tb_ring_stop(net->tx_ring.ring); - tbnet_free_buffers(&net->rx_ring); - tbnet_free_buffers(&net->tx_ring); - + /* Tear the paths down before stopping the rings. This mirrors + * tbnet_connected_work(), which enables the paths last so the + * Rx ring is primed before packets can arrive. Stopping a + * ring zeroes its descriptor base and tbnet_free_buffers() + * unmaps and frees the frame buffers, leaving anything still + * in flight with nowhere to drain to; + * __tb_path_deactivate_hop() then waits for the hop's + * 'pending' bit, which on some host routers never clears in + * that state. + */ ret = tb_xdomain_disable_paths(net->xd, net->local_transmit_path, net->tx_ring.ring->hop, @@ -399,6 +404,11 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout) if (ret) netdev_warn(net->dev, "failed to disable DMA paths\n"); + tb_ring_stop(net->rx_ring.ring); + tb_ring_stop(net->tx_ring.ring); + tbnet_free_buffers(&net->rx_ring); + tbnet_free_buffers(&net->tx_ring); + tb_xdomain_release_in_hopid(net->xd, net->remote_transmit_path); net->remote_transmit_path = 0; } From fde39b8a521780391fb4e5bda2c0aa4928947f12 Mon Sep 17 00:00:00 2001 From: Doruk Tan Ozturk Date: Sun, 2 Aug 2026 14:06:02 +0200 Subject: [PATCH 091/116] net: usb: ipheth: fix carrier_work UAF on disconnect ipheth_sndbulk_callback() re-arms the carrier-check work on any non-zero URB status: else schedule_delayed_work(&dev->carrier_work, 0); Nothing ties that to the interface being up, so the work can be armed again after ipheth_close() has already drained it, and stay armed until the netdev whose private area embeds it is freed. On unplug with a TX URB in flight, ipheth_disconnect() drains the work through unregister_netdev() -> ipheth_close() -> cancel_delayed_work_sync() and only then calls ipheth_kill_urbs(). usb_kill_urb() completes the in-flight TX URB with -ENOENT, so ipheth_sndbulk_callback() runs after the drain and re-arms carrier_work. The same completion also re-arms the work if the interface is only brought down while a TX URB is in flight, and ipheth_carrier_check_work() then keeps re-queueing itself once a second. unregister_netdev() does not call ipheth_close() for an already-down interface, so nothing drains it on the later unplug either. In both cases free_netdev() frees the netdev while carrier_work is still pending, and ipheth_carrier_check_work() dereferences freed memory. Tie the work to the interface state instead of chasing the completion: disable it in ipheth_close() and enable it in ipheth_open(), so a schedule_delayed_work() from the URB completion is a no-op whenever the interface is not up. disable_delayed_work_sync() also waits for a running instance, so it fully replaces the cancel_delayed_work_sync() it takes the place of. The work starts out disabled in ipheth_probe() so the enable/disable counts balance from the first open. Reproduced under KASAN on linux-next (next-20260731) with dummy_hcd and raw-gadget standing in for the device, driving the second path above (the interface is already down, so unregister_netdev() does not call ipheth_close()): 15 of 15 unpatched boots report a slab-use-after-free in __run_timers(), freed by ipheth_disconnect() and re-armed from ipheth_sndbulk_callback() via queue_delayed_work_on(). The same trigger on a kernel differing only by this patch reports 0 of 15, and the carrier check still functions across open/close cycles. The reproducer needs an attached USB device that stops draining bulk OUT, plus a link down and unplug, driven as root. It is not a privilege boundary crossing and no exploit primitive was developed. Found by 0sec (https://0sec.ai). Fixes: bb1b40c7cb86 ("usbnet: ipheth: prevent TX queue timeouts when device not ready") Cc: stable@vger.kernel.org Signed-off-by: Doruk Tan Ozturk Link: https://patch.msgid.link/20260802120602.42595-1-doruk@0sec.ai Signed-off-by: Jakub Kicinski --- drivers/net/usb/ipheth.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index bb1364f85bd1..2b490114d232 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -490,6 +490,7 @@ static int ipheth_open(struct net_device *net) if (retval) return retval; + enable_delayed_work(&dev->carrier_work); schedule_delayed_work(&dev->carrier_work, IPHETH_CARRIER_CHECK_TIMEOUT); return retval; } @@ -499,7 +500,11 @@ static int ipheth_close(struct net_device *net) struct ipheth_device *dev = netdev_priv(net); netif_stop_queue(net); - cancel_delayed_work_sync(&dev->carrier_work); + /* A TX URB can still complete with an error after this point and + * try to re-arm the carrier work. Disable it instead of cancelling + * it, so that such a schedule_delayed_work() is a no-op. + */ + disable_delayed_work_sync(&dev->carrier_work); return 0; } @@ -629,6 +634,10 @@ static int ipheth_probe(struct usb_interface *intf, } INIT_DELAYED_WORK(&dev->carrier_work, ipheth_carrier_check_work); + /* Armed only between ipheth_open() and ipheth_close(). Start out + * disabled so the enable/disable counts balance from the first open. + */ + disable_delayed_work(&dev->carrier_work); retval = ipheth_alloc_urbs(dev); if (retval) { From 35772b4981f38ba8059372cde8753e8e477e98ec Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 3 Aug 2026 18:16:33 +0200 Subject: [PATCH 092/116] mptcp: options: reset DSS fields in case of unexpected size A remote peer could send a malformed DSS with a wrong size, followed by another DSS or MPC + Data. In this case, the first suboption will be ignored, but leaving some fields written, which could lead to inconsistency or access uninitialized data. Explicitly reset the fields that could have been modified in case of unexpected size. Link: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260728-net-mptcp-misc-fixes-7-2-rc6-v1-0-f7e2d229159d%40kernel.org?part=1 Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-1-b8f496d71664@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c664023d37ba..038eca33c6b1 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -188,8 +188,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, * RFC 8684 Section 3.3.0 checks later in subflow_data_ready */ if (opsize != expected_opsize && - opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) + opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { + mp_opt->dsn64 = 0; + mp_opt->use_map = 0; + mp_opt->ack64 = 0; + mp_opt->use_ack = 0; + mp_opt->data_fin = 0; break; + } mp_opt->suboptions |= OPTION_MPTCP_DSS; if (mp_opt->use_ack) { From b6ee361524641f57b2e2363f7737f20e17f67827 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 3 Aug 2026 18:16:34 +0200 Subject: [PATCH 093/116] mptcp: avoid combining some incoming suboptions Some MPTCP suboptions are mutually exclusive according to the RFC8684, but also because in different places, the code doesn't expect some combinations to be present. That's specially true for suboptions that would be present twice, but with different attributes. The new restrictions are the same as the ones applied on the output side, with mptcp_write_options. The same rules can be reused with a small fix: an MP_FASTCLOSE can be used with a DSS when the sender picks this option [1], which is not the case on Linux. Here are the rules: Which options can be used together? X: mutually exclusive O: often used together C: can be used together in some cases P: could be used together but we prefer not to (optimisations) | Opt: | MPC | MPJ | DSS | ADD | RM | PRIO | FAIL | FC | |------|------|------|------|------|------|------|------|------| | MPC |------|------|------|------|------|------|------|------| | MPJ | X |------|------|------|------|------|------|------| | DSS | X | X |------|------|------|------|------|------| | ADD | X | X | P |------|------|------|------|------| | RM | C | C | C | P |------|------|------|------| | PRIO | X | C | C | C | C |------|------|------| | FAIL | X | X | C | X | X | X |------|------| | FC | X | X | P | X | X | X | X |------| | RST | X | X | X | X | X | X | O | O | |------|------|------|------|------|------|------|------|------| The only difference is with the 'P': another stack could send and ADD_ADDR with other suboptions (DSS, RM_ADDR), and this should be allowed. A few points of attention: - In theory, an MP_CAPABLE could be used with a RM_ADDR, but there is no reason to add it with a SYN. Note that even with a 4th ACK, it doesn't seem to be useful, except when IDs are known in advance via another channel. Better not to break that. - Now, combining both an MP_CAPABLE and an MP_JOIN will no longer result to a reject of the two options, but only the second suboption is ignored. That seems OK to do that for this unexpected error. At least now all inconsistent combinations are handled the same way. This could change later in next. This also means the explicit checks for having both MPC + MPJ in subflow.c will now be unreachable. That's fine, they will be removed in a follow-up patch. - In case of conflicting combinations, the extra suboption(s) is/are ignored: having such combinations either means the remote peer is buggy, or is evil. The simplest action is then taken in this case: stop processing the current suboption. - In mp_opt->suboptions, there is also a bit reserved to the checksum, which can be used in an MP_CAPABLE and a DSS. Each time a DSS option can be used in parallel with another option, the checksum can be set, so the verification is combined into a new OPTIONS_MPTCP_DSS macro. - An MP_CAPABLE ACK can carry a Data-Level Length, and an optional Checksum: they are the same as the ones found in a DSS, because a DSS cannot be used in parallel to an MP_CAPABLE. Similarly, even if there is room, a DSS cannot be used with an MP_JOIN. Fixes: eda7acddf808 ("mptcp: Handle MPTCP TCP options") Cc: stable@vger.kernel.org Link: https://www.rfc-editor.org/rfc/rfc8684.html#section-3.5-5.1 [1] Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-2-b8f496d71664@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 59 +++++++++++++++++++++++++++++++++++++++++++- net/mptcp/protocol.h | 1 + 2 files changed, 59 insertions(+), 1 deletion(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 038eca33c6b1..1057d500577b 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -50,6 +50,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, } } + /* Only the MPC + ACK can be used with a RM_ADDR */ + if (subopt == OPTION_MPTCP_MPC_ACK) { + if ((mp_opt->suboptions & ~OPTION_MPTCP_RM_ADDR) != 0) + break; + } else if (mp_opt->suboptions != 0) { + break; + } + /* Cfr RFC 8684 Section 3.3.0: * If a checksum is present but its use had * not been negotiated in the MP_CAPABLE handshake, the receiver MUST @@ -122,6 +130,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_JOIN: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + if (opsize == TCPOLEN_MPTCP_MPJ_SYN) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; @@ -153,6 +166,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_DSS: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO | + OPTION_MPTCP_FASTCLOSE | + OPTION_MPTCP_FAIL)) != 0) + break; + pr_debug("DSS\n"); ptr++; @@ -240,6 +261,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_ADD_ADDR: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + mp_opt->echo = (*ptr++) & MPTCP_ADDR_ECHO; if (!mp_opt->echo) { if (opsize == TCPOLEN_MPTCP_ADD_ADDR || @@ -299,6 +326,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_RM_ADDR: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_MPC_ACK | + OPTIONS_MPTCP_MPJ | + OPTIONS_MPTCP_DSS | + OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + if (opsize < TCPOLEN_MPTCP_RM_ADDR_BASE + 1 || opsize > TCPOLEN_MPTCP_RM_ADDR_BASE + MPTCP_RM_IDS_MAX) break; @@ -313,6 +348,13 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_PRIO: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_MPJ | + OPTIONS_MPTCP_DSS | + OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_RM_ADDR)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_PRIO) break; @@ -322,6 +364,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_FASTCLOSE: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RST)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_FASTCLOSE) break; @@ -333,6 +380,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_RST: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_FAIL | + OPTION_MPTCP_FASTCLOSE)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_RST) break; @@ -348,6 +400,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_FAIL: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RST)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_FAIL) break; @@ -1406,7 +1463,7 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, * RM | C | C | C | P |------|------|------|------| * PRIO | X | C | C | C | C |------|------|------| * FAIL | X | X | C | X | X | X |------|------| - * FC | X | X | X | X | X | X | X |------| + * FC | X | X | P | X | X | X | X |------| * RST | X | X | X | X | X | X | O | O | * ------|------|------|------|------|------|------|------|------| * diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 4a2d40cd7b13..c13680d18994 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -37,6 +37,7 @@ OPTION_MPTCP_MPC_ACK) #define OPTIONS_MPTCP_MPJ (OPTION_MPTCP_MPJ_SYN | OPTION_MPTCP_MPJ_SYNACK | \ OPTION_MPTCP_MPJ_ACK) +#define OPTIONS_MPTCP_DSS (OPTION_MPTCP_DSS | OPTION_MPTCP_CSUMREQD) /* MPTCP option subtypes */ #define MPTCPOPT_MP_CAPABLE 0 From 900e6d80548e69be7ffd358122790fbaa458a9b4 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 3 Aug 2026 18:16:35 +0200 Subject: [PATCH 094/116] mptcp: remove MPC && MPJ check After the parent commit ("mptcp: avoid combining some incoming suboptions"), the parsing step no longer allow to have both the MP_CAPABLE and MP_JOIN suboptions set together. These chunks are now unreachable, these checks can then be removed. Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-3-b8f496d71664@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8e386899ceb9..e1f20ff8fdb4 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -174,8 +174,6 @@ static int subflow_check_req(struct request_sock *req, if (unlikely(listener->pm_listener)) return subflow_reset_req_endp(req, skb); - if (opt_mp_join) - return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); @@ -277,9 +275,6 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK); opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK); - if (opt_mp_capable && opt_mp_join) - return -EINVAL; - if (opt_mp_capable && listener->request_mptcp) { if (mp_opt.sndr_key == 0) return -EINVAL; From a7aad5b69d3bdaec20a3ed9284e184502450c0cd Mon Sep 17 00:00:00 2001 From: Qing Luo Date: Mon, 3 Aug 2026 18:16:36 +0200 Subject: [PATCH 095/116] mptcp: pm: fix data race in add_addr timer callback The timer callback reads entry->retrans_times outside pm.lock to decide whether to call mptcp_pm_subflow_established(). Since mptcp_pm_announced_del_timer() can concurrently set retrans_times = ADD_ADDR_RETRANS_MAX under pm.lock, a race condition exists. I discovered this issue while studying the code. AI tools helped me to verify the issue can potentially happen under race conditions. Use a local 'retransmit' flag set inside pm.lock to capture whether retransmission is still possible when the lock is taken. This allows to call mptcp_pm_subflow_established() accordingly, and not depending on the situation that can be different when checked outside the pm.lock. Fixes: 348d5c1dec60 ("mptcp: move to next addr when timeout") Cc: stable@vger.kernel.org Signed-off-by: Qing Luo Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-4-b8f496d71664@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 6afd39aea110..c71dcf887683 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -380,6 +380,7 @@ static void mptcp_pm_add_addr_timer(struct timer_list *timer) struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; unsigned int timeout = 0; + bool retransmit; pr_debug("msk=%p\n", msk); @@ -412,14 +413,15 @@ static void mptcp_pm_add_addr_timer(struct timer_list *timer) entry->retrans_times++; } - if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) + retransmit = entry->retrans_times < ADD_ADDR_RETRANS_MAX; + if (retransmit) timeout <<= entry->retrans_times; else timeout = 0; spin_unlock_bh(&msk->pm.lock); - if (entry->retrans_times == ADD_ADDR_RETRANS_MAX) + if (!retransmit) mptcp_pm_subflow_established(msk); out: From ca318e7bbb7723f57bcd9e69a2873b5884435552 Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Mon, 3 Aug 2026 18:16:37 +0200 Subject: [PATCH 096/116] selftests: mptcp: join: mark tests with data corruption as failed check_transfer() compares the input and output files byte-by-byte using `cmp -l "$in" "$out" | while read ...`. Because the while-loop body runs in a subshell (the script sets neither lastpipe nor pipefail), the fail_test call inside it -- which sets the global ret/last_test_failed -- and the `return 1` both act on the subshell, not on check_transfer(). check_transfer() thus always falls through to `return 0`, and any data corruption affecting only the payload (leaving the subflow/PM counters untouched) is silently reported as PASS. Fixes: 8117dac3e7c3 ("selftests: mptcp: add invert check in check_transfer") Cc: stable@vger.kernel.org Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-5-b8f496d71664@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c0aeffd5cb71..7dc91fac4917 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -584,7 +584,7 @@ check_transfer() mv "$tmpfile" "$out" tmpfile="" fi - cmp -l "$in" "$out" | while read -r i a b; do + while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then fail_test "$what does not match (in, out):" @@ -595,7 +595,7 @@ check_transfer() else print_info "$what has inverted byte at ${i}" fi - done + done < <(cmp -l "$in" "$out") return 0 } From efc33b5102ff859bacd390a5f30112d8e0c084c0 Mon Sep 17 00:00:00 2001 From: Shardul Bankar Date: Mon, 3 Aug 2026 18:16:38 +0200 Subject: [PATCH 097/116] mptcp: pm: fix memory leak from alloc-during-teardown race mptcp_pm_destroy() empties msk->pm.anno_list and msk->pm.userspace_pm_local_addr_list under msk->pm.lock during socket teardown, dropping the lock between the two. A concurrent userspace PM genl ANNOUNCE on the same msk holds a sock reference via mptcp_token_get_sock() and, in mptcp_pm_nl_announce_doit(), calls mptcp_userspace_pm_append_new_local_addr() and mptcp_pm_announced_alloc(). Both take msk->pm.lock briefly to add to their respective lists. Because the genl handler holds a sock reference, mptcp_pm_destroy() may run on the same msk via mptcp_disconnect(), which invokes mptcp_destroy_common() without dropping the sock refcount, before the handler completes. If the lock acquisitions interleave such that mptcp_pm_destroy() empties a list first, the later alloc adds its entry to a list head that nothing else iterates for this msk, and the entry leaks. kmemleak reports both mptcp_pm_add_addr objects (from mptcp_pm_announced_alloc()) and mptcp_pm_addr_entry objects (from mptcp_userspace_pm_append_new_local_addr()) under sustained concurrent ANNOUNCE + close load against the userspace PM. Add an MPTCP_PM_DESTROYING bit in msk->pm.status, set by mptcp_pm_destroy() under pm.lock before the lists are emptied and checked under pm.lock by the alloc paths. Either the alloc takes pm.lock first, in which case its entry is on the list when mptcp_pm_destroy() frees it; or mptcp_pm_destroy() takes pm.lock first, in which case the later alloc observes the bit and refuses. Found by an MPTCP protocol-flow harness extending BRF (arXiv:2305.08782). Fixes: 9ab4807c84a4 ("mptcp: netlink: Add MPTCP_PM_CMD_ANNOUNCE") Cc: stable@vger.kernel.org Signed-off-by: Shardul Bankar Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-6-b8f496d71664@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 13 +++++++++++-- net/mptcp/pm_userspace.c | 4 ++++ net/mptcp/protocol.h | 7 ++++--- 3 files changed, 19 insertions(+), 5 deletions(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index c71dcf887683..64a1236aabee 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -443,6 +443,9 @@ bool mptcp_pm_announced_alloc(struct mptcp_sock *msk, lockdep_assert_held(&msk->pm.lock); + if (msk->pm.status & BIT(MPTCP_PM_DESTROYING)) + return false; + add_entry = mptcp_pm_announced_lookup(msk, addr); if (add_entry) { if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) @@ -1145,10 +1148,16 @@ void mptcp_pm_worker(struct mptcp_sock *msk) void mptcp_pm_destroy(struct mptcp_sock *msk) { + spin_lock_bh(&msk->pm.lock); + msk->pm.status |= BIT(MPTCP_PM_DESTROYING); + spin_unlock_bh(&msk->pm.lock); + mptcp_pm_free_announced_list(msk); - if (mptcp_pm_is_userspace(msk)) - mptcp_userspace_pm_free_local_addr_list(msk); + /* Free the userspace local address list unconditionally: the socket + * can be reused (mptcp_disconnect()) and re-selected to a different PM + */ + mptcp_userspace_pm_free_local_addr_list(msk); } void mptcp_pm_data_reset(struct mptcp_sock *msk) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 945aa5afc2dd..2203cc2d2748 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -54,6 +54,10 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, bitmap_zero(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_lock_bh(&msk->pm.lock); + if (msk->pm.status & BIT(MPTCP_PM_DESTROYING)) { + ret = -EINVAL; + goto append_err; + } mptcp_for_each_userspace_pm_addr(msk, e) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); if (addr_match && entry->addr.id == 0 && needs_id) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index c13680d18994..1b80f2d6ec5a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -190,9 +190,10 @@ enum mptcp_pm_status { MPTCP_PM_ESTABLISHED, MPTCP_PM_SUBFLOW_ESTABLISHED, MPTCP_PM_ALREADY_ESTABLISHED, /* persistent status, set after ESTABLISHED event */ - MPTCP_PM_MPC_ENDPOINT_ACCOUNTED /* persistent status, set after MPC local address is - * accounted int id_avail_bitmap - */ + MPTCP_PM_MPC_ENDPOINT_ACCOUNTED, /* persistent status, set after MPC local address is + * accounted int id_avail_bitmap + */ + MPTCP_PM_DESTROYING, /* To fence out PM list allocs */ }; enum mptcp_pm_type { From e00b63056fb4f261455b3e5df5268a1f8ce47a87 Mon Sep 17 00:00:00 2001 From: Wyatt Feng Date: Mon, 3 Aug 2026 18:16:39 +0200 Subject: [PATCH 098/116] mptcp: fastopen: only mark MPTFO subflows with SYN data Passive TCP Fast Open accepts a valid-cookie SYN even when it carries no data. In that case the child socket's receive queue is intentionally left empty. mptcp_fastopen_subflow_synack_set_params() set is_mptfo before checking for queued SYN data. That made data-less TFO SYNs hit a WARN and, if the warning was non-fatal, left stale MPTFO state behind. The stale flag could later trigger a state-confusion bug in check_fully_established(). Only mark the subflow as MPTFO after confirming that an SKB was queued. Return quietly when the receive queue is empty. Note that mptcp_subflow_context's is_mptfo field is now not just about subflows where the TFO was present, but about MPTFO subflow that consumed SYN data. Only having a valid cookie but not carrying data is not really "doing TFO". Fixes: 36b122baf6a8 ("mptcp: add subflow_v(4,6)_send_synack()") Cc: stable@vger.kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Zhengchuan Liang Reported-by: Xin Liu Signed-off-by: Wyatt Feng Signed-off-by: Ren Wei Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-7-b8f496d71664@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/fastopen.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 082c46c0f50e..f717750906ff 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -24,12 +24,13 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf sk = subflow->conn; tp = tcp_sk(ssk); - subflow->is_mptfo = 1; - + /* A valid TFO cookie does not guarantee SYN data. */ skb = skb_peek(&ssk->sk_receive_queue); - if (WARN_ON_ONCE(!skb)) + if (!skb) return; + subflow->is_mptfo = 1; + /* dequeue the skb from sk receive queue */ __skb_unlink(skb, &ssk->sk_receive_queue); skb_ext_reset(skb); From 41b49a8b914ec7dcb03eae93fb27f3c464078644 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 3 Aug 2026 18:16:40 +0200 Subject: [PATCH 099/116] mptcp: reclaim forward-allocated memory on RX path errors After commit 9db5b3cec4ec ("mptcp: borrow forward memory from subflow"), errors in the receive path prior to queueing skbs into the receive queue do not trigger forward-allocated memory reclaiming. Prevent forward memory from growing unboundedly in pathological drop scenarios by explicitly reclaiming memory when skbs are dropped. Fixes: 9db5b3cec4ec ("mptcp: borrow forward memory from subflow") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-8-b8f496d71664@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index ca644ec53eed..7c8180d8d5ef 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -149,6 +149,12 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) static void mptcp_drop(struct sock *sk, struct sk_buff *skb) { + /* The skb forward memory was already transferred to sk by + * mptcp_borrow_fwdmem(), even before setting the destructor. + */ + if (!skb->destructor) + sk_mem_reclaim(sk); + sk_drops_skbadd(sk, skb); __kfree_skb(skb); } From e48e8edbef2eb824201495daa5234560f632b23c Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Mon, 3 Aug 2026 20:15:32 +0800 Subject: [PATCH 100/116] xdp: reject clones that overrun skb_shared_info tailroom xdpf_clone() clones broadcast copies into a single page and sets frame_sz to PAGE_SIZE. __xdp_build_skb_from_frame() later treats that page like a normal XDP frame and expects the usual skb_shared_info tailroom at the end of the buffer. The current check only rejects frames whose linear xdp_frame header, headroom, and packet data exceed PAGE_SIZE. A source frame backed by a larger allocation can still satisfy that check while extending into the clone's required shared-info area. When such a clone is converted back into an skb, build_skb_around() places skb_shared_info over live packet bytes and later writes can corrupt XDP return metadata. Reject clones unless their linear area fits inside SKB_WITH_OVERHEAD(PAGE_SIZE), matching the tailroom requirement already enforced by the XDP-to-skb conversion path. Fixes: e624d4ed4aa8 ("xdp: Extend xdp_redirect_map with broadcast support") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zhiling Zou Link: https://patch.msgid.link/6b2afef5d1738763c6965e8e466eb16e43e4f956.1785757386.git.zhilinz@nebusec.ai Signed-off-by: Jakub Kicinski --- net/core/xdp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/xdp.c b/net/core/xdp.c index 9890a30584ba..0194e69da339 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -871,7 +871,7 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) headroom = xdpf->headroom + sizeof(*xdpf); totalsize = headroom + xdpf->len; - if (unlikely(totalsize > PAGE_SIZE)) + if (unlikely(totalsize > SKB_WITH_OVERHEAD(PAGE_SIZE))) return NULL; page = dev_alloc_page(); if (!page) From 7bca91d63341274e857f4aeaad54d229405e93dc Mon Sep 17 00:00:00 2001 From: chanyoung Date: Tue, 4 Aug 2026 14:28:35 +0900 Subject: [PATCH 101/116] tls: don't leave a full plaintext sk_msg ring unpushed When the copy path in tls_sw_sendmsg_locked() adds the fragment that fills the plaintext sk_msg ring, it does not set full_record, so the record is left full and unpushed. A later splice() then adds to an already full ring: sk_msg_page_add() has no fullness check of its own, so sg.end wraps onto sg.start and the ring appears empty. Fragments added after that overwrite live entries, and sg.size no longer matches what is reachable between sg.start and sg.end, so pushing the record runs the scatterwalk off the end of the scatterlist. An unprivileged user can trigger this on a loopback TCP socket with the "tls" ULP attached: BUG: kernel NULL pointer dereference, address: 0000000000000008 RIP: 0010:memcpy_from_scatterwalk+0x32/0xc0 Call Trace: skcipher_walk_next+0x1d1/0x2c0 gcm_encrypt_aesni_avx+0x1e9/0x220 bpf_exec_tx_verdict+0x3bb/0x860 tls_sw_sendmsg+0xa1a/0xca0 __sys_sendto+0x1da/0x1f0 Set full_record in the copy path when the ring becomes full, and push a record that is already full on entry to the sendmsg loop. Suggested-by: Sabrina Dubroca Fixes: fe1e81d4f73b ("tls/sw: Support MSG_SPLICE_PAGES") Cc: stable@vger.kernel.org Signed-off-by: chanyoung Link: https://patch.msgid.link/20260804052837.49015-2-ppoo1220@gmail.com Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d4afc90fd796..d2e399be8ef6 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -832,6 +832,14 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; + /* open record may be full if we couldn't push it in the last sendmsg call */ + if (sk_msg_full(msg_pl)) { + full_record = true; + sk_msg_trim(sk, msg_en, + msg_pl->sg.size + prot->overhead_size); + goto copied; + } + alloc_encrypted: ret = tls_alloc_encrypted_msg(sk, required_size); if (ret) { @@ -921,6 +929,12 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, msg_pl, try_to_copy); if (ret < 0) goto trim_sgl; + + if (sk_msg_full(msg_pl)) { + full_record = true; + sk_msg_trim(sk, msg_en, + msg_pl->sg.size + prot->overhead_size); + } } /* Open records defined only if successfully copied, otherwise From 3834e079d67feda5fd57d1ea8d4185d316997335 Mon Sep 17 00:00:00 2001 From: chanyoung Date: Tue, 4 Aug 2026 14:28:36 +0900 Subject: [PATCH 102/116] selftests: tls: add a test for splicing onto a full plaintext record Splicing onto a plaintext sk_msg ring that is already full used to wrap the ring and make the kernel oops in the scatterwalk once the record was pushed. Only the copy path leaves the ring full without pushing it, so splice until the ring is one fragment short, add the last fragment with a one-byte MSG_MORE send, and splice once more before pushing the record. CONFIG_MAX_SKB_FRAGS is 17..45, so that last fragment follows between 16 and 44 splices; sweep that range to trigger the bug on any build. Signed-off-by: chanyoung Link: https://patch.msgid.link/20260804052837.49015-3-ppoo1220@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 37 +++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index cbdd3ea28b99..3d6f553eaf97 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -835,6 +835,43 @@ TEST_F(tls, send_and_splice) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_onto_full_record) +{ + char mem_send[4608]; + char mem_recv[4608]; + int frag_len = 100; + int nfrags, i, off; + int p[2]; + + memrnd(mem_send, sizeof(mem_send)); + ASSERT_GE(pipe(p), 0); + + for (nfrags = 16; nfrags <= 44; nfrags++) { + for (i = 0, off = 0; i < nfrags; i++, off += frag_len) { + EXPECT_EQ(write(p[1], mem_send + off, frag_len), frag_len); + EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, frag_len, + SPLICE_F_MORE), frag_len); + } + + EXPECT_EQ(send(self->fd, mem_send + off, 1, MSG_MORE), 1); + off++; + + EXPECT_EQ(write(p[1], mem_send + off, frag_len), frag_len); + EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, frag_len, + SPLICE_F_MORE), frag_len); + off += frag_len; + + EXPECT_EQ(send(self->fd, mem_send + off, 1, 0), 1); + off++; + + EXPECT_EQ(recv(self->cfd, mem_recv, off, MSG_WAITALL), off); + EXPECT_EQ(memcmp(mem_send, mem_recv, off), 0); + } + + close(p[0]); + close(p[1]); +} + TEST_F(tls, splice_to_pipe) { int send_len = TLS_PAYLOAD_MAX_LEN; From 1c8629651cb54f7b51db8fc0b1a9944e4a4b0f5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Jean?= Date: Tue, 4 Aug 2026 12:55:28 +0000 Subject: [PATCH 103/116] tls: rx: restore msg_iter before TLS 1.3 optimistic retry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit tls_decrypt_sg() advances msg->msg_iter when it maps user pages for the optimistic TLS 1.3 zero-copy path. If the decrypted record turns out not to be unpadded application data, tls_decrypt_sw() retries into a kernel skb, but leaves the iterator advanced. The subsequent copy from the skb then writes decrypted bytes again at a later point in the caller iovecs while recvmsg() reports only the post-retry length. A TLS peer can trigger this after the receiver enables TLS_RX_EXPECT_NO_PAD. Revert the iterator by the number of bytes consumed by the optimistic mapping before retrying without zero-copy. Add a selftest which sends a TLS 1.3 control record with TLS_RX_EXPECT_NO_PAD enabled and verifies that recvmsg() does not overwrite later iovecs beyond the returned length. Fixes: ce61327ce989 ("tls: rx: support optimistic decrypt to user buffer with TLS 1.3") Cc: stable@vger.kernel.org Signed-off-by: Jérémy Jean Link: https://patch.msgid.link/20260804125528.2139928-1-Jeremy.Jean@oss.cyber.gouv.fr Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 2 ++ tools/testing/selftests/net/tls.c | 57 +++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d2e399be8ef6..133ed7c89402 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1456,6 +1456,8 @@ tls_decrypt_sw(struct sock *sk, struct tls_context *tls_ctx, /* If opportunistic TLS 1.3 ZC failed retry without ZC */ if (unlikely(darg->zc && prot->version == TLS_1_3_VERSION && darg->tail != TLS_RECORD_TYPE_DATA)) { + iov_iter_revert(&msg->msg_iter, strp_msg(darg->skb)->full_len - + prot->overhead_size); darg->zc = false; if (!darg->tail) TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXNOPADVIOL); diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 3d6f553eaf97..a0e72e402748 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1839,6 +1839,63 @@ TEST_F(tls, recv_efault) } #define TLS_RECORD_TYPE_HANDSHAKE 0x16 + +TEST_F(tls_basic, recvmsg_nopad_retry_iov) +{ + char payload[32]; + char first_iov[sizeof(payload)]; + char later_iov[sizeof(payload) * 2]; + char expected_later_iov[sizeof(later_iov)]; + char cbuf[CMSG_SPACE(sizeof(char))]; + struct tls_crypto_info_keys tls13; + struct iovec iov[] = { + { .iov_base = first_iov, .iov_len = sizeof(first_iov) }, + { .iov_base = later_iov, .iov_len = sizeof(later_iov) }, + }; + struct msghdr msg = { + .msg_iov = iov, + .msg_iovlen = ARRAY_SIZE(iov), + .msg_control = cbuf, + .msg_controllen = sizeof(cbuf), + }; + int one = 1; + int ret; + int i; + + if (self->notls) + SKIP(return, "no TLS support"); + + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls13, 0); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls13, tls13.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls13, tls13.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX_EXPECT_NO_PAD, + &one, sizeof(one)); + ASSERT_EQ(ret, 0); + + for (i = 0; i < sizeof(payload); i++) + payload[i] = 0x40 + i; + memset(first_iov, 0xa5, sizeof(first_iov)); + memset(later_iov, 0x5a, sizeof(later_iov)); + memset(expected_later_iov, 0x5a, sizeof(expected_later_iov)); + + /* A control record forces optimistic TLS 1.3 RX to retry. */ + ret = tls_send_cmsg(self->fd, TLS_RECORD_TYPE_HANDSHAKE, + payload, sizeof(payload), 0); + ASSERT_EQ(ret, sizeof(payload)); + + ret = recvmsg(self->cfd, &msg, 0); + ASSERT_EQ(ret, sizeof(payload)); + EXPECT_EQ(memcmp(first_iov, payload, sizeof(payload)), 0); + EXPECT_EQ(memcmp(later_iov, expected_later_iov, + sizeof(later_iov)), 0); +} + /* key_update, length 1, update_not_requested */ static const char key_update_msg[] = "\x18\x00\x00\x01\x00"; static void tls_send_keyupdate(struct __test_metadata *_metadata, int fd) From 6b69f2ef10cdb018c0b127a7cab88e590bbddba4 Mon Sep 17 00:00:00 2001 From: Ahmad Byagowi Date: Tue, 4 Aug 2026 14:07:51 -0700 Subject: [PATCH 104/116] ptp: ocp: Fix board ID over-read The EEPROM board ID is a fixed 13-byte field and is not guaranteed to contain a NUL terminator. Passing it directly to devlink_info_version_fixed_put() treats it as a C string and may read beyond the field. Format at most OCP_BOARD_ID_LEN bytes into the existing local buffer before reporting the ID. Use a precision limit because the snprintf() output size alone does not bound the source string scan. Fixes: 0cfcdd1ebcfe ("ptp: ocp: add nvmem interface for accessing eeprom") Cc: stable@vger.kernel.org Signed-off-by: Ahmad Byagowi Reviewed-by: Vadim Fedorenko Link: https://patch.msgid.link/20260804210751.48248-1-ahmadexp@gmail.com Signed-off-by: Jakub Kicinski --- drivers/ptp/ptp_ocp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 35e911f1ad78..3d26ec1f7b9e 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -2177,9 +2177,11 @@ ptp_ocp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, if (err) return err; + snprintf(buf, sizeof(buf), "%.*s", OCP_BOARD_ID_LEN, + (const char *)bp->board_id); err = devlink_info_version_fixed_put(req, DEVLINK_INFO_VERSION_GENERIC_BOARD_ID, - bp->board_id); + buf); if (err) return err; From bfec39ff1484b4e9f7d93bc4580fdb634bbc7d19 Mon Sep 17 00:00:00 2001 From: Bhargava Marreddy Date: Wed, 5 Aug 2026 15:10:22 +0530 Subject: [PATCH 105/116] bnge: Fix resource leak in bnge_init_nic() error path If bnge_init_chip() fails, bnge_init_nic() jumps to err_free_ring_grps and returns immediately, skipping cleanup for RX ring pair buffers. Remove the early return so execution falls through to err_free_rx_ring_pair_bufs to properly free resources on error. Fixes: 23df6aebf803 ("bng_en: Allocate stat contexts") Signed-off-by: Bhargava Marreddy Reviewed-by: Dharmender Garg Reviewed-by: Rajashekar Hudumula Link: https://patch.msgid.link/20260805094022.15487-1-bhargava.marreddy@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnge/bnge_netdev.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c index 6f7ef506d4e1..ac4c93e5b634 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c @@ -2768,8 +2768,6 @@ static int bnge_init_nic(struct bnge_net *bn) err_free_ring_grps: bnge_free_ring_grps(bn); - return rc; - err_free_rx_ring_pair_bufs: bnge_free_rx_ring_pair_bufs(bn); return rc; From 3b9a324e646d3657a8d9806dfbfe4f3e4066e882 Mon Sep 17 00:00:00 2001 From: Qihang Tang Date: Wed, 5 Aug 2026 20:57:27 +0800 Subject: [PATCH 106/116] net: remove CAP_SYS_RAWIO zero-padding in dev_validate_header dev_validate_header() reads dev->hard_header_len directly when zero-padding short link layer headers for CAP_SYS_RAWIO holders: if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); return true; } Packet send paths call dev_validate_header() on skbs whose headroom was allocated from an earlier hard_header_len read. If the device is reconfigured so that dev->hard_header_len increases before validation, the memset writes past the reserved buffer, an out-of-bounds write. This out-of-bounds write is masked in some SOCK_RAW paths today because the same concurrent increase can first make skb_push() exceed the reserved headroom and trigger skb_under_panic(). Remove the zero-padding branch before making those hard_header_len reads consistent, so the snapshot fixes do not turn a loud panic into a silent overwrite. This path is only reached for variable length L2 protocols, where len < hard_header_len but len >= min_header_len. No remaining in-tree variable length L2 protocol implements header_ops->validate, and the CAP_SYS_RAWIO bypass that zero-pads and accepts short headers has no real value beyond allowing testing of intentionally malformed input. Drop the CAP_SYS_RAWIO branch. The remaining reads of dev->hard_header_len in dev_validate_header() are comparisons only and have no memory safety impact. Suggested-by: Willem de Bruijn Fixes: 2793a23aacbd ("net: validate variable length ll headers") Cc: stable@vger.kernel.org Signed-off-by: Qihang Tang Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260805125729.19220-2-q.h.hack.winter@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9981d637f8b5..9a770eb823ce 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3531,11 +3531,6 @@ static inline bool dev_validate_header(const struct net_device *dev, if (len < dev->min_header_len) return false; - if (capable(CAP_SYS_RAWIO)) { - memset(ll_header + len, 0, dev->hard_header_len - len); - return true; - } - if (dev->header_ops && dev->header_ops->validate) return dev->header_ops->validate(ll_header, len); From 03390aa32e669cc4ecd7d34108e2e1afc13d689d Mon Sep 17 00:00:00 2001 From: Qihang Tang Date: Wed, 5 Aug 2026 20:57:28 +0800 Subject: [PATCH 107/116] packet: use consistent hard_header_len in non-ring send paths packet_snd() reads dev->hard_header_len multiple times while allocating and constructing an skb. Device reconfiguration can change this value concurrently, for example through bonding device type changes. For SOCK_RAW, packet_snd() can save a larger value in reserve and later allocate headroom using a smaller value. Moving skb->data back by reserve then places it before skb->head, and the following copy from userspace can attempt an out-of-bounds write. packet_sendmsg_spkt() has the same issue because it calculates its reservation and header offset from separate reads before dropping the RCU read lock to allocate the skb. Add LL_RESERVED_SPACE_EX() for callers that already saved a header length. Read hard_header_len once in packet_snd() and use it for allocation and construction. In packet_sendmsg_spkt(), preserve the allocation-time value through the device lookup retry. The separate SOCK_DGRAM consistency problem between hard_header_len and header_ops->create is not addressed here. Fixes: b84bbaf7a6c8 ("packet: in packet_snd start writing at link layer allocation") Cc: stable@vger.kernel.org Signed-off-by: Qihang Tang Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260805125729.19220-3-q.h.hack.winter@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 6 ++++-- net/packet/af_packet.c | 26 ++++++++++++++++---------- 2 files changed, 20 insertions(+), 12 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9a770eb823ce..8840b126979f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -300,9 +300,11 @@ struct hh_cache { * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ -#define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ +#define LL_RESERVED_SPACE_EX(dev, hlen) \ + ((((hlen) + READ_ONCE((dev)->needed_headroom)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) +#define LL_RESERVED_SPACE(dev) \ + LL_RESERVED_SPACE_EX(dev, (dev)->hard_header_len) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0e1355be89f6..b7af45c809e4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1966,8 +1966,9 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; - int err; + int hard_header_len; int extra_len = 0; + int err; /* * Get and verify the address. @@ -2010,14 +2011,18 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, extra_len = 4; /* We're doing our own CRC */ } + /* Keep the allocation-time header length across retry. */ + if (!skb) + hard_header_len = READ_ONCE(dev->hard_header_len); + err = -EMSGSIZE; - if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) + if (len > dev->mtu + hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { - size_t reserved = LL_RESERVED_SPACE(dev); + size_t reserved = LL_RESERVED_SPACE_EX(dev, hard_header_len); int tlen = dev->needed_tailroom; - unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; + unsigned int hhlen = dev->header_ops ? hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); @@ -2047,7 +2052,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, err = -EINVAL; goto out_unlock; } - if (len > (dev->mtu + dev->hard_header_len + extra_len) && + if (len > (dev->mtu + hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; @@ -2969,7 +2974,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); - int hlen, tlen, linear; + int hard_header_len, hlen, tlen, linear; int extra_len = 0; /* @@ -3009,8 +3014,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; } + hard_header_len = READ_ONCE(dev->hard_header_len); if (sock->type == SOCK_RAW) - reserve = dev->hard_header_len; + reserve = hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) @@ -3031,10 +3037,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; err = -ENOBUFS; - hlen = LL_RESERVED_SPACE(dev); + hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); - linear = max(linear, min_t(int, len, dev->hard_header_len)); + linear = max(linear, min_t(int, len, hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) @@ -3050,7 +3056,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && - dev->min_header_len != dev->hard_header_len) + dev->min_header_len != hard_header_len) skb_reset_network_header(skb); } From 21b5953e7494c16a42e6cd8cf110e18d13ae4a6b Mon Sep 17 00:00:00 2001 From: Qihang Tang Date: Wed, 5 Aug 2026 20:57:29 +0800 Subject: [PATCH 108/116] packet: use consistent hard_header_len in TX_RING send path tpacket_snd() reads dev->hard_header_len independently for skb allocation and header construction in tpacket_fill_skb(). Concurrent netdevice reconfiguration can therefore make the reserved headroom smaller than the amount later pushed, or make copylen - hard_header_len negative. Snapshot hard_header_len once before processing ring frames and use it for the frame limit, headroom allocation, copy length, and skb construction. Pass the snapshot to tpacket_fill_skb(). The separate SOCK_DGRAM consistency problem between hard_header_len and header_ops->create is not addressed here. Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap") Cc: stable@vger.kernel.org Signed-off-by: Qihang Tang Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260805125729.19220-4-q.h.hack.winter@gmail.com Signed-off-by: Jakub Kicinski --- net/packet/af_packet.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b7af45c809e4..435756877aba 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2587,6 +2587,7 @@ static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, + int hard_header_len, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; @@ -2618,8 +2619,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); - skb_push(skb, dev->hard_header_len); - skb_put(skb, copylen - dev->hard_header_len); + skb_push(skb, hard_header_len); + skb_put(skb, copylen - hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; @@ -2750,7 +2751,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; - int hlen, tlen, copylen = 0; + int hard_header_len, hlen, tlen, copylen = 0; long timeo; mutex_lock(&po->pg_vec_lock); @@ -2797,8 +2798,9 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_put; } + hard_header_len = READ_ONCE(dev->hard_header_len); if (po->sk.sk_socket->type == SOCK_RAW) - reserve = dev->hard_header_len; + reserve = hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2835,7 +2837,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; - hlen = LL_RESERVED_SPACE(dev); + hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { data += vnet_hdr_sz; @@ -2853,10 +2855,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) vnet_hdr.hdr_len); has_vnet_hdr = true; } - copylen = max_t(int, copylen, dev->hard_header_len); + copylen = max_t(int, copylen, hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + - (copylen - dev->hard_header_len), + (copylen - hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { @@ -2866,7 +2868,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, - addr, hlen, copylen, &sockc); + addr, hlen, copylen, hard_header_len, + &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && From b1896543ce59c4258625a35cf41e23a9a1f80ea2 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Wed, 5 Aug 2026 15:10:43 +0200 Subject: [PATCH 109/116] s390/ism: Fix UAF of sba and ieq during ism_dev_exit() A ism interrupt handler can be active in parallel with ism_dev_exit(), accessing freed data structures. No new interrupts will be generated after unregister_ieq(). Drain ongoing interrupt handlers by free_irq(), before freeing ism data structures. Fixes: 684b89bc39ce ("s390/ism: add device driver for internal shared memory") Signed-off-by: Alexandra Winter Link: https://patch.msgid.link/20260805131043.954639-1-wintera@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/s390/net/ism_drv.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index d99c588d3e00..242da20f27e0 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -148,13 +148,16 @@ static int unregister_sba(struct ism_dev *ism) if (ret && ret != ISM_ERROR) return -EIO; + return 0; +} + +static void ism_free_sba(struct ism_dev *ism) +{ dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, ism->sba, ism->sba_dma_addr); ism->sba = NULL; ism->sba_dma_addr = 0; - - return 0; } static int unregister_ieq(struct ism_dev *ism) @@ -168,13 +171,16 @@ static int unregister_ieq(struct ism_dev *ism) if (ret && ret != ISM_ERROR) return -EIO; + return 0; +} + +static void ism_free_ieq(struct ism_dev *ism) +{ dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, ism->ieq, ism->ieq_dma_addr); ism->ieq = NULL; ism->ieq_dma_addr = 0; - - return 0; } static int ism_read_local_gid(struct dibs_dev *dibs) @@ -573,6 +579,7 @@ static int ism_dev_init(struct ism_dev *ism) unreg_sba: unregister_sba(ism); + ism_free_sba(ism); free_irq: free_irq(pci_irq_vector(pdev, 0), ism); free_vectors: @@ -585,9 +592,13 @@ static void ism_dev_exit(struct ism_dev *ism) { struct pci_dev *pdev = ism->pdev; + /* ism will only generate new IRQs while ieq & sba are registered */ unregister_ieq(ism); unregister_sba(ism); + /* drain ongoing irpt handlers */ free_irq(pci_irq_vector(pdev, 0), ism); + ism_free_ieq(ism); + ism_free_sba(ism); pci_free_irq_vectors(pdev); } From d0c80dbb970439bd2eeb0e5effff8c16a5f4e1e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 5 Aug 2026 13:15:08 +0000 Subject: [PATCH 110/116] net/atm: fix slab-out-of-bounds read in vcc_setsockopt() vcc_setsockopt() contained an ineffective optlen check: if (__SO_LEVEL_MATCH(optname, level) && optlen != __SO_SIZE(optname)) return -EINVAL; If __SO_LEVEL_MATCH(optname, level) evaluated to false (e.g. if the caller passed a mismatched level), the length check optlen != __SO_SIZE(optname) was short-circuited and bypassed. Execution then fell through to switch(optname), calling copy_from_sockptr() assuming optval contained sufficient space. Furthermore, even if level matched, a cgroup BPF setsockopt filter could shrink optlen after entry. Because copy_from_sockptr() on kernel pointers uses memcpy(), this leads to a KASAN slab-out-of-bounds read when optlen is smaller than the expected structure size. Fix this by using copy_safe_from_sockptr(), which unconditionally validates that optlen is at least the expected size before copying. Also change the local 'value' variable type from 'unsigned long' to 'int' so that SO_SETCLP matches its sizeof(int) ABI encoding on 64-bit systems. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+53ecc09fb81df10ef4de@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=53ecc09fb81df10ef4de Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260805131508.3227331-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/atm/common.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/atm/common.c b/net/atm/common.c index c7f92405daf0..81195727fa18 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -710,7 +710,7 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct atm_vcc *vcc; - unsigned long value; + int value; int error; if (__SO_LEVEL_MATCH(optname, level) && optlen != __SO_SIZE(optname)) @@ -722,8 +722,10 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, { struct atm_qos qos; - if (copy_from_sockptr(&qos, optval, sizeof(qos))) - return -EFAULT; + error = copy_safe_from_sockptr(&qos, sizeof(qos), optval, + optlen); + if (error) + return error; error = check_qos(&qos); if (error) return error; @@ -737,8 +739,10 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, return 0; } case SO_SETCLP: - if (copy_from_sockptr(&value, optval, sizeof(value))) - return -EFAULT; + error = copy_safe_from_sockptr(&value, sizeof(value), optval, + optlen); + if (error) + return error; if (value) vcc->atm_options |= ATM_ATMOPT_CLP; else From c9158ceaf27780ef64534ad72f44ffde3f8ccc49 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 5 Aug 2026 11:18:40 -0400 Subject: [PATCH 111/116] sctp: clear control chunk transport if it is being removed sctp_make_heartbeat_ack() caches the destination transport in chunk->transport without taking a reference. When src_out_of_asoc_ok is enabled, the HEARTBEAT ACK may remain queued on control_chunk_list instead of being transmitted immediately. If the peer transport is removed while the chunk is still queued, sctp_assoc_rm_peer() drops the transport and schedules it for RCU freeing, but only clears cached transport pointers in out_chunk_list. The queued control chunk therefore retains a dangling transport pointer. Once an ASCONF_ACK clears the suppression and the queued control chunk is transmitted, SCTP dereferences the stale transport pointer, leading to a use-after-free. Fix this by also clearing chunk->transport for queued control chunks in control_chunk_list when removing the transport. Fixes: 8a07eb0a50ae ("sctp: Add ASCONF operation on the single-homed host") Reported-by: Daniele Linguaglossa Signed-off-by: Xin Long Link: https://patch.msgid.link/7e1168cb722132152a29d47e5eafaeac4a3bf6f3.1785943120.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/sctp/associola.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b6ac0966420a..5b0ae616e1ff 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -573,6 +573,10 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, if (ch->transport == peer) ch->transport = NULL; + list_for_each_entry(ch, &asoc->outqueue.control_chunk_list, list) + if (ch->transport == peer) + ch->transport = NULL; + asoc->peer.transport_count--; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_REMOVED, 0); From 03a736fde464cefa0a6e10d29914c27635965ce2 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Wed, 5 Aug 2026 17:54:25 +0200 Subject: [PATCH 112/116] MAINTAINERS: dpll: zl3073x: replace Prathosh Satish with Min Li Replace Prathosh Satish by Min Li as the Microchip co-maintainer of the ZL3073X DPLL driver. Signed-off-by: Ivan Vecera Link: https://patch.msgid.link/20260805155425.38808-1-ivecera@redhat.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index a77cf599bac2..9de29cdcd8c6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17847,7 +17847,7 @@ F: drivers/net/wireless/microchip/ MICROCHIP ZL3073X DRIVER M: Ivan Vecera -M: Prathosh Satish +M: Min Li L: netdev@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/dpll/microchip,zl30731.yaml From 8e63c9e6179ace3033dcd19991f95386e9d3130f Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 6 Aug 2026 11:07:58 +0300 Subject: [PATCH 113/116] net: Defer netdev KOBJ_ADD uevent until the device is published netdev_register_kobject() calls device_add(), which emits KOBJ_ADD and wakes udev, but register_netdevice() only makes the device findable by name later, in list_netdevice(). A udev worker that reacts to the uevent can therefore run against a device that no lookup can find yet. This used to be harmless because the ethtool ioctl took the rtnl_lock when looking the device up, and register_netdevice() runs under rtnl, so the worker simply blocked until registration finished. The commit in the fixes tag moved the lookup out from under rtnl for ops-locked drivers. Now there is a short window in register_netdevice() between netdev_register_kobject() until list_netdevice() when the device is not findable by name. This was reproduced with the mlx5 driver on a kernel with KASAN enabled during devlink reload: systemd-udevd's net_driver builtin gets -ENODEV from ETHTOOL_GDRVINFO, which was preventing interface renaming. Suppress the uevent in netdev_register_kobject() and emit it from register_netdevice() next to rtmsg_ifinfo(). This is the last point in register_netdevice() where no error can happen, so only fully registered devices are announced: the registration error paths never reach it, and the device_del() that unwinds them stays silent as well, leaving userspace with neither an add nor a remove. Fixes: f994752b1127 ("net: ethtool: optionally skip rtnl_lock on IOCTL path") Signed-off-by: Dragos Tatulea Reviewed-by: Shahar Shitrit Link: https://patch.msgid.link/20260806080758.2039586-2-dtatulea@nvidia.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 1 + net/core/net-sysfs.c | 14 ++++++++++++++ net/core/net-sysfs.h | 1 + 3 files changed, 16 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index 5933c5dab09e..c49d2ce51285 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -11494,6 +11494,7 @@ int register_netdevice(struct net_device *dev) * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ + netdev_uevent_add(dev); if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing)) rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 0e71c9ed41e8..25546deacec8 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -2334,6 +2334,9 @@ int netdev_register_kobject(struct net_device *ndev) *groups++ = &wireless_group; #endif /* CONFIG_SYSFS */ + /* Hold back the KOBJ_ADD uevent until the device is listed. */ + dev_set_uevent_suppress(dev, 1); + error = device_add(dev); if (error) return error; @@ -2349,6 +2352,17 @@ int netdev_register_kobject(struct net_device *ndev) return error; } +/* Announce a fully registered device to userspace. This pairs with the uevent + * suppression from netdev_register_kobject(). + */ +void netdev_uevent_add(struct net_device *ndev) +{ + struct device *dev = &ndev->dev; + + dev_set_uevent_suppress(dev, 0); + kobject_uevent(&dev->kobj, KOBJ_ADD); +} + /* Change owner for sysfs entries when moving network devices across network * namespaces owned by different user namespaces. */ diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 38e2e3ffd0bd..2f41a4dee866 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -4,6 +4,7 @@ int __init netdev_kobject_init(void); int netdev_register_kobject(struct net_device *); +void netdev_uevent_add(struct net_device *dev); void netdev_unregister_kobject(struct net_device *); int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); int netdev_queue_update_kobjects(struct net_device *net, From d31c14e56a4f01f0689c29c0bcbcd45f65b4a473 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 5 Aug 2026 19:28:21 -0700 Subject: [PATCH 114/116] net: avoid theoretical races with ref drain Technically, it's illegal to take a ref on a netdev just because we have a pointer on which we already hold a ref, with no other protection. This is because our simple per-cpu refcount implementation cannot atomically read the count. Let's make sure we cancel outstanding work and never queue more work for a device we know is dead. This way taking a ref on a dev we know is on the netdev_work_list is always going to be safe. Jiangshan Yi reports that the issues is caught by ref tracker infra leading to a warning: WARNING: lib/ref_tracker.c:322 at ref_tracker_free WARNING: lib/ref_tracker.c:246 at ref_tracker_dir_exit Reported-by: Jiangshan Yi Link: https://lore.kernel.org/20260731035135.3917308-2-yijiangshan@kylinos.cn Fixes: 12c765be84d2 ("net: turn the rx_mode work into a generic netdev_work facility") Link: https://patch.msgid.link/20260806022821.2079945-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- net/core/dev.c | 1 + net/core/dev.h | 1 + net/core/netdev_work.c | 16 ++++++++++++++++ 3 files changed, 18 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index c49d2ce51285..af260ff5462a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -12436,6 +12436,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); dev_memory_provider_uninstall(dev); + netdev_work_cancel_all(dev); netdev_unlock_ops(dev); bpf_dev_bound_netdev_unregister(dev); diff --git a/net/core/dev.h b/net/core/dev.h index 5d0b0305d3ba..b757faead4d1 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -179,6 +179,7 @@ enum netdev_work_core { void __netdev_work_core_sched(struct net_device *dev, unsigned long event); unsigned long __netdev_work_core_cancel(struct net_device *dev, unsigned long mask); +void netdev_work_cancel_all(struct net_device *dev); void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, unsigned int gchanges, u32 portid, diff --git a/net/core/netdev_work.c b/net/core/netdev_work.c index 3109fae132ad..e721a06d58df 100644 --- a/net/core/netdev_work.c +++ b/net/core/netdev_work.c @@ -31,6 +31,10 @@ static void netdev_work_enqueue(struct net_device *dev, unsigned long events, return; spin_lock_bh(&netdev_work_lock); + if (!dev_isalive(dev)) { + spin_unlock_bh(&netdev_work_lock); + return; + } if (list_empty(&dev->work_node)) { list_add_tail(&dev->work_node, &netdev_work_list); netdev_hold(dev, &dev->work_tracker, GFP_ATOMIC); @@ -61,6 +65,18 @@ netdev_work_dequeue(struct net_device *dev, unsigned long *pending, return events; } +void netdev_work_cancel_all(struct net_device *dev) +{ + spin_lock_bh(&netdev_work_lock); + dev->work_pending = 0; + dev->work_core_pending = 0; + if (!list_empty(&dev->work_node)) { + list_del_init(&dev->work_node); + netdev_put(dev, &dev->work_tracker); + } + spin_unlock_bh(&netdev_work_lock); +} + void netdev_work_sched(struct net_device *dev, unsigned long events) { netdev_work_enqueue(dev, events, 0); From af0e5cdd031f4f4a8f6d4160bfbda4f36872b0ed Mon Sep 17 00:00:00 2001 From: Maximilian Immanuel Brandtner Date: Wed, 5 Aug 2026 08:22:48 +0200 Subject: [PATCH 115/116] tls: don't abort the connection on signal-interrupted sends When a signal interrupts a blocking send, tls_tx_records() treats the resulting -ERESTARTSYS as a transmission failure and marks the socket errored via tls_err_abort() with the raw error code. Later syscalls return the kernel-internal errno 512 (ERESTARTSYS) to userspace, as the signal it stems from is no longer pending during syscall exit and thus never translated. An interrupted send is not a connection error: the partially sent record stays queued and is resent later. Interrupt error codes are therefore excluded from the abort in the same way as -EAGAIN. Fixes: b341ca51d267 ("tls: Fix tls_sw_sendmsg error handling") Signed-off-by: Maximilian Immanuel Brandtner Link: https://patch.msgid.link/20260805063109.1772314-1-maxbr@linux.ibm.com Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 133ed7c89402..62d46736e24b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags) } tx_err: - if (rc < 0 && rc != -EAGAIN) + if (rc < 0 && rc != -EAGAIN && rc != -EINTR && rc != -ERESTARTSYS) tls_err_abort(sk, rc); return rc; From b0ce5fd9fabe7c79463cf4602217d4dfeff5b1fd Mon Sep 17 00:00:00 2001 From: Philipp David Date: Tue, 4 Aug 2026 15:22:03 -0700 Subject: [PATCH 116/116] igc: fix netdev not re-attached after resume if interface is down __igc_resume() calls netif_device_attach() only inside the netif_running() branch, so an interface that was down during suspend is never re-attached on resume. It then stays in the not-present state that __igc_shutdown() set via netif_device_detach(): ethtool reports ENODEV and every attempt to bring the interface up fails the netif_device_present() check in __dev_open() with -ENODEV, silently, since __igc_resume() returns 0. Only reloading the driver recovers the device. This is easy to hit in practice because NetworkManager brings managed interfaces down before sleep unless Wake-on-LAN is configured, making the adapter unusable after every suspend/resume cycle with WoL disabled. Re-attach the netdev on every successful resume, as igb and e1000e do. Fixes: 6f31d6b643a3 ("igc: Refactor runtime power management flow") Cc: stable@vger.kernel.org Signed-off-by: Philipp David Reviewed-by: Aleksandr Loktionov Reviewed-by: Dima Ruinskiy Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260804222205.1580328-11-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igc/igc_main.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 16fcc8cf6191..39043d8ca1bf 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7585,11 +7585,13 @@ static int __igc_resume(struct device *dev, bool rpm) err = __igc_open(netdev, true); if (!rpm) rtnl_unlock(); - if (!err) - netif_device_attach(netdev); + if (err) + return err; } - return err; + netif_device_attach(netdev); + + return 0; } static int igc_resume(struct device *dev)